{"as_of":"2026-08-14T17:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d5a7a983f73384ad63a3d8312930f9087ab6accdd9af545e810f854a974d2d6f","coverage":[{"denominator":86,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":86,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T10:56:17.053263Z","state":"measured"},{"denominator":87,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":87,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-01T05:35:48.896721Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T10:25:41.148374Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"cited_work":{"arxiv_id":"2601.08303","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.08303","snapshot_observed_at":"2026-07-07T03:18:52.304329Z","title":"arXiv preprint arXiv:2601.08303 (2026)","venue":null,"work_id":"e92ea1de-e6a0-4e2f-8a15-ea2a83fe28c7","year":2026},"citing_paper":{"arxiv_id":"2606.32020","last_updated":"2026-06-30T17:51:26Z","snapshot_observed_at":"2026-08-03T10:16:58.559510Z","submitted_at":"2026-06-30T17:51:26Z","title":"Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-01T05:35:48.896721Z"},"links":{"cited_paper":"/paper/2601.08303","citing_paper":"/paper/2606.32020"},"observation_digest":"sha256:887dd9ba59126a4d377ff5cca2045ff51c077d2c31f1631906541b9ebbff2157","observation_id":"92172935-1aa5-44c7-824e-941088bda5d7","resolution":{"observed_at":"2026-07-07T03:18:52.304329Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2601.08303/citation-record","integrity":"/paper/2601.08303/integrity","json":"/paper/2601.08303/citation-record.json","paper":"/paper/2601.08303"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.386646Z","title":"Stable diffusion 3.5","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.386646Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:53254e1ba81418dc7400299b63a3e09bbc87f52286778d5d28f73d9c53712978","observation_id":"e97814fc-2d53-45ee-b043-46d7264f553f","resolution":{"observed_at":"2026-08-03T10:56:11.386646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.424526Z","title":"GQA: Training generalized multi-query transformer models from multi-head checkpoints","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.424526Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:827b20dfbe4c38894d15d938a3fd7f00cf428db273c7b88095836f5a5f4c66b7","observation_id":"3c04d5d7-09cb-419e-8ba4-e73faa4517aa","resolution":{"observed_at":"2026-08-03T10:56:11.424526Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.466461Z","title":"Sd3.5- flash: Distribution-guided distillation of generative flows,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.466461Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:f694ece5b6026f2add21dee3c00d9c7ab0a4dd9e322c4a7e733aa1fd7e0aa32f","observation_id":"a978448a-83ad-4930-9b7e-68a1b0805090","resolution":{"observed_at":"2026-08-03T10:56:11.466461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.522639Z","title":"All are worth words: A vit backbone for diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.522639Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:70aa527a2f7aa055621ff7f541dd8cdfe4351accc0cdbaf895ab7bc5b379da9a","observation_id":"531885fc-5da1-4efc-b67f-d957cf63c934","resolution":{"observed_at":"2026-08-03T10:56:11.522639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.565290Z","title":"All are worth words: A vit backbone for diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.565290Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:a840430cb6f1e64c7fae9f02cdade7ca4268fda74c6a7dfc569b07ae474fee73","observation_id":"2a9ff00b-8056-493d-832b-ad53890ea9c2","resolution":{"observed_at":"2026-08-03T10:56:11.565290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.580720Z","title":"Large scale gan training for high fidelity natural image synthe- sis","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.580720Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:e70966b7212cfc79d8a2170bcfef17bf4c19e85709c34dd179a41fb5086d8653","observation_id":"5e7a5cfd-5d54-41f1-9332-a5b9e62e5c85","resolution":{"observed_at":"2026-08-03T10:56:11.580720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.654430Z","title":"Once-for-all: Train one network and specialize it for efficient deployment","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.654430Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:c60035e32e0d196e6e16a276c83a2aa29b6dffa19dda7bef8b438a396684ee75","observation_id":"f0cf8a1f-ffdf-4b55-9dca-509e08e826a6","resolution":{"observed_at":"2026-08-03T10:56:11.654430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22705","last_updated":"2025-05-28T17:59:15Z","snapshot_observed_at":"2026-08-14T05:30:11.702159Z","submitted_at":"2025-05-28T17:59:15Z","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22705","snapshot_observed_at":"2026-08-03T10:56:11.698369Z","title":"Hidream-i1: A high-efficient image generative foundation model with sparse diffusion transformer.arXiv preprint arXiv:2505.22705, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.698369Z"},"links":{"cited_paper":"/paper/2505.22705","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:74f27fc258a7f2c3370c70a18e041abbd20413663883b3efd144422eec77ee9b","observation_id":"25fe78e3-36bc-4bbf-90ce-80ced33227f9","resolution":{"observed_at":"2026-08-03T10:56:11.698369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11925","last_updated":"2024-04-18T06:02:54Z","snapshot_observed_at":"2026-08-13T00:27:40.134533Z","submitted_at":"2024-04-18T06:02:54Z","title":"EdgeFusion: On-Device Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11925","snapshot_observed_at":"2026-08-03T10:56:11.764930Z","title":"EdgeFusion: On-Device Text-to-Image Generation.arXiv preprint arXiv:2404.11925, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.764930Z"},"links":{"cited_paper":"/paper/2404.11925","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:4a205a58a694d1340cd7edc93664e258d9f6c196f53fc4721dd8d23f5ac7df47","observation_id":"fec04d08-9a6b-4289-a498-0e4ef6b55ca2","resolution":{"observed_at":"2026-08-03T10:56:11.764930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04692","last_updated":"2024-03-17T16:59:25Z","snapshot_observed_at":"2026-08-13T00:59:54.489440Z","submitted_at":"2024-03-07T17:41:37Z","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04692","snapshot_observed_at":"2026-08-03T10:56:11.852224Z","title":"Pixart-σ: Weak-to-strong training of dif- fusion transformer for 4k text-to-image generation.arXiv preprint arXiv:2403.04692, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.852224Z"},"links":{"cited_paper":"/paper/2403.04692","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:17022ce53d142ed2bb77f084d5f44fae0f18a7b0a28f59168dcd465fa0f5a316","observation_id":"f5421e55-af37-428a-8e1a-7ea89fc9132b","resolution":{"observed_at":"2026-08-03T10:56:11.852224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.894002Z","title":"Pixart-α: Fast training of dif- fusion transformer for photorealistic text-to-image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.894002Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:283e4683e9d651b791b147b8edbdab102ed320d5ecd39098b283933ed98c1e4d","observation_id":"f61f53a6-57af-4cac-827d-07746378352d","resolution":{"observed_at":"2026-08-03T10:56:11.894002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.931068Z","title":"Sana-sprint: One-step diffusion with continuous-time con- sistency distillation, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.931068Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:eaef232b336f6224bc657ad56d3b1bd47a1a7a8925c55f927faac7c9a9091a7d","observation_id":"a54e030b-a9d7-4c61-a8bf-798bd1f3550d","resolution":{"observed_at":"2026-08-03T10:56:11.931068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.957443Z","title":"Scalable high-resolution pixel-space image syn- thesis with hourglass diffusion transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.957443Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:be38b1cef9343a707cfcf7b389a80dd70539f2f12af22dcf31b536e417a5d749","observation_id":"f91b811b-e907-4297-8d12-82adf11533f6","resolution":{"observed_at":"2026-08-03T10:56:11.957443Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:11.996242Z","title":"Transformers are SSMs: Gen- eralized models and efficient algorithms through structured state space duality","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:11.996242Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:82a116a7cf8d9fde47eaf4d1028ce8fb6d2e0ec09febb0d312d4039a468e4194","observation_id":"27562a3e-4609-4ef0-aa32-00bf91d9a5c6","resolution":{"observed_at":"2026-08-03T10:56:11.996242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.021264Z","title":"Deepfloyd.https://github.com/deep-floyd/IF,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.021264Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:b516253b50c8a0396c54f3660f2b2c6361bcf50d6f57e50302c1ed91b731eabe","observation_id":"80dd09cf-6cb1-4ac8-92d4-2b69f7a0b725","resolution":{"observed_at":"2026-08-03T10:56:12.021264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.066246Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.066246Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:2f783ac567e35a2b69044b7c2e561f295b525e5f2f337b0d4542d10a56d14c45","observation_id":"601e65fd-c153-4774-8dbc-a26dab476976","resolution":{"observed_at":"2026-08-03T10:56:12.066246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.115197Z","title":"Kakade, Ali Farhadi, and Prateek Jain","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.115197Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:2af036f0c98574d2d0ca557be78c8fb505c03d22f3526d7515c769574fc4c9eb","observation_id":"afb08000-f073-45b3-b6c3-ff3af2003188","resolution":{"observed_at":"2026-08-03T10:56:12.115197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.158450Z","title":"Scaling rectified flow trans- formers for high-resolution image synthesis, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.158450Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:1a7d9b830a97ca611a65f285380bb39602e88eefe3ec03f5d1e5ca817118c35f","observation_id":"9c7e2b69-e7b3-4ebd-867e-5387a0efad6a","resolution":{"observed_at":"2026-08-03T10:56:12.158450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.203422Z","title":"Geneval: An object-focused framework for evaluating text- to-image alignment.Advances in Neural Information Pro- cessing Systems, 36, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.203422Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:8feb660ae39a0a12275ebba9387be4d75ea82cf0049b8f26399ddd71f12fb19e","observation_id":"d31673e2-9eb7-468f-bf62-e95271aadcec","resolution":{"observed_at":"2026-08-03T10:56:12.203422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.253507Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.253507Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:f1d36e23906c2369f771f4c99d4213415a3a6955269ed0fca191213e74f6444e","observation_id":"9d8056fe-98b8-4688-9cc5-8d57e265e236","resolution":{"observed_at":"2026-08-03T10:56:12.253507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-03T10:56:12.284686Z","title":"Mamba: Linear-time sequence modeling with selective state spaces.arXiv preprint arXiv:2312.00752, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.284686Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:69fa6b6523287426c9156b82b97438ba723c12d81fca0f40c45725c2b2859c02","observation_id":"8ee94792-7bf9-42e3-8ba9-100838b22ada","resolution":{"observed_at":"2026-08-03T10:56:12.284686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.16922","last_updated":"2025-04-23T17:49:53Z","snapshot_observed_at":"2026-08-13T08:58:27.010977Z","submitted_at":"2025-04-23T17:49:53Z","title":"Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.16922","snapshot_observed_at":"2026-08-03T10:56:12.360059Z","title":"Generalized neighborhood attention: Multi-dimensional sparse attention at the speed of light.arXiv preprint arXiv:2504.16922, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.360059Z"},"links":{"cited_paper":"/paper/2504.16922","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:0856ffeb92c86f91cfcdfe690799957e923e0f7ccd28b0b28039f20ef4d85dbf","observation_id":"9efae607-6b48-414c-a57b-c0177c9a57e7","resolution":{"observed_at":"2026-08-03T10:56:12.360059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.393518Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilib- rium.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.393518Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:5b196d0b477d2b36bd554d7e04860852b00a2c0cbdb495fed46c2af568b5f3b2","observation_id":"7b36c497-9ba4-4823-9fcd-1f858210b13c","resolution":{"observed_at":"2026-08-03T10:56:12.393518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.427996Z","title":"Denoising diffu- sion probabilistic models.Advances in Neural Information Processing Systems (NeurIPS), 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.427996Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:77ab0a5ec00216bd50440b969ccb1e4bd0b4a68551db2be7b7561c1aea775534","observation_id":"ed8b0c87-364b-46ae-8524-b1ae087f41b3","resolution":{"observed_at":"2026-08-03T10:56:12.427996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.481318Z","title":"sim- ple diffusion: End-to-end diffusion for high resolution im- ages","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.481318Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:44b9243064351351d63bcc95440a8f45f316842df9c2fafaed7a7a648865f6d4","observation_id":"7bce88a7-f12e-4308-ad12-edeea00237bf","resolution":{"observed_at":"2026-08-03T10:56:12.481318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.513233Z","title":"Simpler diffu- sion: 1.5 fid on imagenet512 with pixel-space diffusion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.513233Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:c350d27ebf36693c02ad1a82e018864dde76cb9b4f873f3dcd7eebb1f8294b33","observation_id":"3307d102-66d0-4921-9204-53e31c9cad5e","resolution":{"observed_at":"2026-08-03T10:56:12.513233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.549522Z","title":"Dynabert: Dynamic bert with adaptive width and depth","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.549522Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:d7dd5e8024ad4734a970bd71cbf10101876e666ce82d3c005953f4da7b631a20","observation_id":"cf57ca3e-51c0-4bc6-b884-4e49ac9d31dc","resolution":{"observed_at":"2026-08-03T10:56:12.549522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09619","last_updated":"2024-12-12T18:59:53Z","snapshot_observed_at":"2026-08-13T20:41:16.231958Z","submitted_at":"2024-12-12T18:59:53Z","title":"SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09619","snapshot_observed_at":"2026-08-03T10:56:12.602318Z","title":"Chan, Mingming Gong, Sergey Tulyakov, Anil Kag, Yanwu Xu, and Jian Ren","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.602318Z"},"links":{"cited_paper":"/paper/2412.09619","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:9cd6fdc7978ac9884b7d23335e651d3a18ff2c11c23a9a3369e50047f8dfff5c","observation_id":"c0213083-55ab-4ce9-ab32-548b70625845","resolution":{"observed_at":"2026-08-03T10:56:12.602318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.641340Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.641340Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:5ae1d316353032f4eb6b7d5e11cfa1e49ac9fb809af62293ddcbe2ddcda4634d","observation_id":"b9e1f8a4-4a45-459a-a0e6-8676889e2d93","resolution":{"observed_at":"2026-08-03T10:56:12.641340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05135","last_updated":"2024-03-08T08:08:10Z","snapshot_observed_at":"2026-08-12T17:58:56.652054Z","submitted_at":"2024-03-08T08:08:10Z","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05135","snapshot_observed_at":"2026-08-03T10:56:12.705471Z","title":"Ella: Equip diffusion models with llm for enhanced semantic alignment.arXiv preprint arXiv:2403.05135, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.705471Z"},"links":{"cited_paper":"/paper/2403.05135","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:8b9e152bb7f89bef3188193c828e257051a6c0c6af65c6dff53e009b151e74ca","observation_id":"43fd62d8-159b-407d-8b2e-ab299f2acc79","resolution":{"observed_at":"2026-08-03T10:56:12.705471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.774499Z","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to- Image Generation .IEEE Transactions on Pattern Analysis Machine Intelligence, (01):1–17, 5555","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.774499Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:8fc8f89de30a02c889934bfdd0b1d1a4733e4d575a63bf3eef26482f47a397e5","observation_id":"341821de-6135-42ed-be52-42fc5e76748e","resolution":{"observed_at":"2026-08-03T10:56:12.774499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.08009","last_updated":"2025-11-10T04:36:27Z","snapshot_observed_at":"2026-08-02T00:07:53.851104Z","submitted_at":"2025-06-09T17:59:55Z","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.08009","snapshot_observed_at":"2026-08-03T10:56:12.818493Z","title":"Self forcing: Bridging the train- test gap in autoregressive video diffusion.arXiv preprint arXiv:2506.08009, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.818493Z"},"links":{"cited_paper":"/paper/2506.08009","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:0a4760ed936cf9b7839ea95080a2ef1fd45da409cb29c4140207db83c878ade6","observation_id":"8bf95d7f-8626-4faf-9050-0149749af736","resolution":{"observed_at":"2026-08-03T10:56:12.818493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.860648Z","title":"TP-blend: Textual-prompt attention pairing for precise object-style blending in diffusion models.Transactions on Machine Learning Research, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.860648Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:948278a025a1ece42d1fa47b030ec766cdeb68e82345e98a90e4ab6908e5ad95","observation_id":"c6780c87-13a6-4b95-9f7a-582552287261","resolution":{"observed_at":"2026-08-03T10:56:12.860648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.04967","last_updated":"2024-11-07T18:43:17Z","snapshot_observed_at":"2026-08-12T22:05:25.180622Z","submitted_at":"2024-11-07T18:43:17Z","title":"AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.04967","snapshot_observed_at":"2026-08-03T10:56:12.920321Z","title":"Ascan: Asymmetric convolution-attention networks for efficient recognition and generation.arXiv preprint arXiv:2411.04967, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.920321Z"},"links":{"cited_paper":"/paper/2411.04967","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:20eff5b4f5a09d2f03e92f8f67862a81066ed41390bcc629aaefede037ae7fb5","observation_id":"c0c87f4c-f57c-47c4-9a49-eecbdfd6e5f9","resolution":{"observed_at":"2026-08-03T10:56:12.920321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:12.984787Z","title":"Bk-sdm: Architecturally Compressed Sta- ble Diffusion for Efficient Text-to-Image Generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:12.984787Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:d6fc7688db7207d9963dc00f114a67b7ee71879e8227b95df88b4f2aaf9ba782","observation_id":"03d3d03c-b063-4026-bb48-5e92f74b0715","resolution":{"observed_at":"2026-08-03T10:56:12.984787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:13.079261Z","title":"Flux: A generative model by black for- est labs.https://github.com/black- forest- labs/flux, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.079261Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:22a0731778469d2c5a7d1a02be66507900b547f08538762b1a04f9177098b7dc","observation_id":"16d7f2e2-59c3-480a-a6f2-ae6a1aeaea8c","resolution":{"observed_at":"2026-08-03T10:56:13.079261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:13.148993Z","title":"Playground v1,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.148993Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:3e9a67c608b2dcdb98cb193ca2b9830432f723e974a390263ce4db4c5159440f","observation_id":"22d20332-4802-417c-af0b-90511cb3f046","resolution":{"observed_at":"2026-08-03T10:56:13.148993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:13.243463Z","title":"Playground v2,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.243463Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:8e5cf9ca3d6016ea84a9149e30135c8651cf07a1808d16082034fa5481991d5a","observation_id":"852ad940-c5b5-4191-a1ba-8ba83c13d50b","resolution":{"observed_at":"2026-08-03T10:56:13.243463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17245","last_updated":"2024-02-27T06:31:52Z","snapshot_observed_at":"2026-07-06T17:36:01.939242Z","submitted_at":"2024-02-27T06:31:52Z","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17245","snapshot_observed_at":"2026-08-03T10:56:13.293248Z","title":"Playground V2","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.293248Z"},"links":{"cited_paper":"/paper/2402.17245","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:4fd86f25b9cb34dfedb25e48acb63dd567d751e10426ca677b2a6405c638b18d","observation_id":"1dbe7838-95e9-4aa1-ad9d-ca904a6a2fc5","resolution":{"observed_at":"2026-08-03T10:56:13.293248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:13.430476Z","title":"Svdquant: Absorbing outliers by low-rank components for 4-bit diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.430476Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:e91aaf26f5ccd7831a5cfa5f41735562334afd889589ce5955f062c25eb9b4c6","observation_id":"9232720f-8924-49ea-b68c-8a34cc8e6856","resolution":{"observed_at":"2026-08-03T10:56:13.430476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:13.445097Z","title":"Snap- fusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds.Advances in Neural Information Pro- cessing Systems, 36, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.445097Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:4f21c9634015004dd1db707ebb950eb410dde5fc710fbeee02a434227cdde99f","observation_id":"d0d02250-aed9-48fe-99e1-7c663fbaec5e","resolution":{"observed_at":"2026-08-03T10:56:13.445097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:13.503017Z","title":"SDXL- Lightning: Progressive Adversarial Diffusion Distillation,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.503017Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:800a8eb79d4fc2f819a908c6bee1e9bbc3ccbb11e18c37d29c9e26da9b18258a","observation_id":"6786d67f-34ba-433c-b92c-7f7693b6415d","resolution":{"observed_at":"2026-08-03T10:56:13.503017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:13.608973Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.608973Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:0bce0a82f413dd648e4412bc62533f2aab832bf91d66ad9bf391bb3917080537","observation_id":"1baacd14-ed3f-4463-bcde-ab2c6c60f5e7","resolution":{"observed_at":"2026-08-03T10:56:13.608973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-02T18:24:58.914589Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-03T10:56:13.668984Z","title":"Flow matching for generative mod- eling.arXiv preprint arXiv:2210.02747, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.668984Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:dd446d0b1b7a590777976fa363a488826b55bc0e501077cd1ef7f443d6a9e52a","observation_id":"7da0cfe9-624d-49e6-ab23-15566f99f0b8","resolution":{"observed_at":"2026-08-03T10:56:13.668984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.10695","last_updated":"2024-10-21T20:01:13Z","snapshot_observed_at":"2026-08-13T17:26:48.873943Z","submitted_at":"2024-09-16T19:52:24Z","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.10695","snapshot_observed_at":"2026-08-03T10:56:13.748789Z","title":"Playground v3: Improving text-to- image alignment with deep-fusion large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.748789Z"},"links":{"cited_paper":"/paper/2409.10695","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:2d24bf54c9c7b6a03ac617d7c385fdabb8a56976db963aed2b196bdffc1127b5","observation_id":"32dab576-631f-471d-9d62-61a173be5449","resolution":{"observed_at":"2026-08-03T10:56:13.748789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08354","last_updated":"2023-05-26T01:40:15Z","snapshot_observed_at":"2026-08-13T12:24:26.357056Z","submitted_at":"2023-03-15T04:14:11Z","title":"Measurement of the branching fraction and $\\it CP$ asymmetry of $B^{0} \\rightarrow \\pi^{0} \\pi^{0}$ decays using $198 \\times 10^6$ $B\\overline{B}$ pairs in Belle II data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08354","snapshot_observed_at":"2026-08-03T10:56:13.911171Z","title":"Magicedit: High-fidelity and temporally coherent video edit- ing.arXiv preprint arXiv:2303.08354, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.911171Z"},"links":{"cited_paper":"/paper/2303.08354","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:9bcd30b83a55e10c4da68c9efcbc8e94d230a10799596ba19174adbf5f2669bc","observation_id":"62e9a878-8b25-404e-b363-e3d7941dfe88","resolution":{"observed_at":"2026-08-03T10:56:13.911171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02097","last_updated":"2024-10-17T08:09:37Z","snapshot_observed_at":"2026-08-12T22:52:07.371453Z","submitted_at":"2024-09-03T17:54:39Z","title":"LinFusion: 1 GPU, 1 Minute, 16K Image","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02097","snapshot_observed_at":"2026-08-03T10:56:13.971631Z","title":"Linfusion: 1 gpu, 1 minute, 16k image.arXiv preprint arXiv:2409.02097, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:13.971631Z"},"links":{"cited_paper":"/paper/2409.02097","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:ea32b8a3d7edc96f7848ca005b8bb231540148dddaced03588f874f4fc1c95c9","observation_id":"3924b6fe-0d69-44da-9a0e-4d67809dc8fa","resolution":{"observed_at":"2026-08-03T10:56:13.971631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-03T10:56:14.028230Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow.arXiv preprint arXiv:2209.03003, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.028230Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:85417fbea193f3584394064dbd5a01763ac6f7ec07a4fec8733d36ef3beb0cd8","observation_id":"9bb3e9e6-0ae1-4265-b6d5-957b6aace0d4","resolution":{"observed_at":"2026-08-03T10:56:14.028230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:14.126353Z","title":"On distillation of guided diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.126353Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:38c44ba23739dfacba9702f21a4bbdb7b231a9718a0118cd8a1af3a05d9b7311","observation_id":"44070e9d-b485-43ac-bcda-bb2cdda49ebe","resolution":{"observed_at":"2026-08-03T10:56:14.126353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:14.236172Z","title":"SDEdit: Guided image synthesis and editing with stochastic differential equa- tions","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.236172Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:f62d44ba61bccf992f441d0002ca260cedfadcdccfe221896452f98d9a1e3c21","observation_id":"bcf87b10-1536-4f35-a7b2-131a2c5d2650","resolution":{"observed_at":"2026-08-03T10:56:14.236172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:14.349190Z","title":"Qwen-image-lightning: Distilled qwen-image models for fast, high-fidelity text-to-image generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.349190Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:2b5d1acf8c898cdb8aa415b956e4b68d3d54e2625d197ad57720352afa82a201","observation_id":"633bdcb1-2786-4cb5-b402-29cf6429a9f4","resolution":{"observed_at":"2026-08-03T10:56:14.349190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:14.377961Z","title":"Kim, Aliaksandr Siarohin, 10 and Anil Kag","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.377961Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:35f9e1822b20c6b5e2a0ce6bbd4cf237315f3b8e3de2fda7f265900badaed594","observation_id":"9c7a05c8-f106-43cf-a5be-b810c91e3fcd","resolution":{"observed_at":"2026-08-03T10:56:14.377961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09748","last_updated":"2023-03-02T09:06:55Z","snapshot_observed_at":"2026-07-06T14:32:37.317828Z","submitted_at":"2022-12-19T18:59:58Z","title":"Scalable Diffusion Models with Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09748","snapshot_observed_at":"2026-08-03T10:56:14.484749Z","title":"Scalable diffusion models with transformers.arXiv preprint arXiv:2212.09748, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.484749Z"},"links":{"cited_paper":"/paper/2212.09748","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:2fb58b2e30f84f87f63b2908951864163f078a3e8768844b3bdf06e1ebae7487","observation_id":"4207589a-5df3-4f09-82fb-71b0e06b7cea","resolution":{"observed_at":"2026-08-03T10:56:14.484749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-08-03T10:56:14.650658Z","title":"Sdxl: Improving latent diffusion mod- els for high-resolution image synthesis.arXiv preprint arXiv:2307.01952, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.650658Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:f122e96869081ab3bca853791b36c875c1bd32825395ef77ffb1dd392fffc404","observation_id":"9440b0be-1177-4a64-ac6e-6730215dfe0a","resolution":{"observed_at":"2026-08-03T10:56:14.650658Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:14.799813Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.799813Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:da4b079f83f6ed73d29d58e8901a7bbf34c2c22b56df917e98842248cd72c1cb","observation_id":"9f2ece9c-66cc-4222-89f1-84e2869e86d2","resolution":{"observed_at":"2026-08-03T10:56:14.799813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:14.917519Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.917519Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:da31410b05b321db8d14de19fd3ccaf2a25baf084a04e725042dd6a5447d07bf","observation_id":"7da8611c-9411-4868-a632-483abdfe94c3","resolution":{"observed_at":"2026-08-03T10:56:14.917519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:14.977469Z","title":"Photorealistic text-to-image diffusion models with deep lan- guage understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:14.977469Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:3cffeaf9673afef1ab6820a052fb949763988ef5f41745340d66646b07750f95","observation_id":"c8335bbc-6740-4b56-8d3e-6ad5b86c5958","resolution":{"observed_at":"2026-08-03T10:56:14.977469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.098361Z","title":"Progressive distillation for fast sampling of diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.098361Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:9d0e4107ec6fe0812edb0822d4b5b718979892f9e0d1a9ec406cb12883fa5d57","observation_id":"c59e5235-0276-4675-b96d-e9e9c681e395","resolution":{"observed_at":"2026-08-03T10:56:15.098361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.02150","last_updated":"2019-11-06T00:19:05Z","snapshot_observed_at":"2026-07-06T08:35:01.386074Z","submitted_at":"2019-11-06T00:19:05Z","title":"Fast Transformer Decoding: One Write-Head is All You Need","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.02150","snapshot_observed_at":"2026-08-03T10:56:15.126250Z","title":"Fast transformer decoding: One write-head is all you need.arXiv preprint arXiv:1911.02150, 2019","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.126250Z"},"links":{"cited_paper":"/paper/1911.02150","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:3a099acdef486441f906ec11bcd64f4350cfd793c8470c262650ac50abc6e5cf","observation_id":"920489a1-6661-4f01-af08-9185245a215c","resolution":{"observed_at":"2026-08-03T10:56:15.126250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.193306Z","title":"Score-based generative modeling through stochastic differential equa- tions.International Conference on Learning Representations (ICLR), 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.193306Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:a28d35d634ce0469f5e343503a2f62338f8ae3252678b5ba8b21b804a911f680","observation_id":"e0a4df26-bba2-4911-91a1-86fa39855ff9","resolution":{"observed_at":"2026-08-03T10:56:15.193306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.254887Z","title":"Consis- tency models.International Conference on Machine Learn- ing (ICML), 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.254887Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:1df50c4a236f89968e3bf46b05cae607cfc601a64d998303f5014fc5c86cb2d6","observation_id":"35f153ab-5f09-41db-8120-0e9c9577a09a","resolution":{"observed_at":"2026-08-03T10:56:15.254887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.288857Z","title":"Bitsfusion: 1.99 bits weight quantization of diffusion model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.288857Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:586472919912006ef3feb11e3668a4cf63550959f5c88e61df038c70e316d536","observation_id":"c5fb46cd-d897-4127-a91b-39587962975b","resolution":{"observed_at":"2026-08-03T10:56:15.288857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.346951Z","title":"Gemma 3n","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.346951Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:8d4851721f9a0aea38264c05314c41569f7d95e9b7eb8794fe3d1d3078ed72be","observation_id":"9efe4566-c09e-4bef-9df4-a64f2816ec23","resolution":{"observed_at":"2026-08-03T10:56:15.346951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.393124Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.393124Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:72d9520656f02eb164082cc26a3d2582cd7685aa602c47275bde9e0b00d3364b","observation_id":"d92d55b5-af21-4786-95e7-cbdfc58b8d51","resolution":{"observed_at":"2026-08-03T10:56:15.393124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.457081Z","title":"U-dits: Downsample tokens in u-shaped diffusion transformers, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.457081Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:c2bfd3a9e75ecb1160e057800f8e8aac344f41945a780c02be0a6c8b9922bbe7","observation_id":"b0ef0d02-1b5a-4edf-84b7-5d8600564d9e","resolution":{"observed_at":"2026-08-03T10:56:15.457081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.515316Z","title":"Sortednet: A scalable and generalized framework for training modular deep neural networks, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.515316Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:c0d0d8a6532e40b39d24e6c7a55e40c2d7da016be2782828f9c4bcc32cba4901","observation_id":"8d56a1a1-9808-43ef-ae1d-f8604c2b96b9","resolution":{"observed_at":"2026-08-03T10:56:15.515316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20314","last_updated":"2025-04-19T02:22:42Z","snapshot_observed_at":"2026-08-12T22:34:51.361078Z","submitted_at":"2025-03-26T08:25:43Z","title":"Wan: Open and Advanced Large-Scale Video Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20314","snapshot_observed_at":"2026-08-03T10:56:15.601188Z","title":"Wan: Open and advanced large-scale video generative models.arXiv preprint arXiv:2503.20314, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.601188Z"},"links":{"cited_paper":"/paper/2503.20314","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:8732e35bcd543db4dbfe98beb93e9deadef56eb19895bb809ad1965eb3a76845","observation_id":"9234a6e7-45bb-4e22-8d40-2af17331a58b","resolution":{"observed_at":"2026-08-03T10:56:15.601188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.18407","last_updated":"2024-12-04T06:18:16Z","snapshot_observed_at":"2026-08-14T10:02:30.655149Z","submitted_at":"2024-05-28T17:47:19Z","title":"Phased Consistency Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18407","snapshot_observed_at":"2026-08-03T10:56:15.654092Z","title":"Phased consistency model.arXiv preprint arXiv:2405.18407, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.654092Z"},"links":{"cited_paper":"/paper/2405.18407","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:2f47d702ab6ac0fed22d6a90a4f41941a10c1b68b9a955376d9564763ba78f52","observation_id":"8a52a8cb-2310-4c5a-9442-b86a21091910","resolution":{"observed_at":"2026-08-03T10:56:15.654092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.691131Z","title":"Hat: Hardware-aware transformers for efficient natural language processing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.691131Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:a53eec969f08467683d8def716632479dceeb68ede3e3f030e30f39644aeea9a","observation_id":"7ab5dc65-bbd7-45ed-a25d-39bbac06976b","resolution":{"observed_at":"2026-08-03T10:56:15.691131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.749674Z","title":"Qwen-image technical report,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.749674Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:7254e9bccd2361abb7fbe9f4eebda7ecbf4a9230fc65b2d7a2178a1928acd06b","observation_id":"2074b4c8-aeb7-470c-832c-1d664b0114e1","resolution":{"observed_at":"2026-08-03T10:56:15.749674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.861695Z","title":"Tinyclip: Clip distillation via affinity mimicking and weight inheritance","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.861695Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:8d3349e11267f206152d71b288213be473df1f08114849f75c63d5d753a85a3d","observation_id":"3f903aba-365a-4bb4-b83b-445209afac02","resolution":{"observed_at":"2026-08-03T10:56:15.861695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.927725Z","title":"Taming diffusion transformer for efficient mobile video gen- eration in seconds, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.927725Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:98aa52e01b123127f2a5cbd02f5a866b160807755fc2ff9262007d7b0228dac7","observation_id":"53db915a-bd20-49ff-8f5b-6b253008e59b","resolution":{"observed_at":"2026-08-03T10:56:15.927725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:15.957850Z","title":"Metaxas, Yanzhi Wang, Sergey Tulyakov, and Jian Ren","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:15.957850Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:a544aaf8055c63db9e17a3715164ec98eb3eadfa004344e26070210902b82c3b","observation_id":"dd7b1508-340e-4561-a844-d0a70ba397eb","resolution":{"observed_at":"2026-08-03T10:56:15.957850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01776","last_updated":"2025-04-27T00:10:11Z","snapshot_observed_at":"2026-08-13T13:28:15.450370Z","submitted_at":"2025-02-03T19:29:16Z","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01776","snapshot_observed_at":"2026-08-03T10:56:16.020021Z","title":"Sparse videogen: Accelerating video diffusion transformers with spatial-temporal sparsity.arXiv preprint arXiv:2502.01776,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.020021Z"},"links":{"cited_paper":"/paper/2502.01776","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:c940ddf024ca4964fb287d6c9b1c8e66b89b7ac88c566cb4dcd17dec3b3abf26","observation_id":"caa6157e-9703-4170-913b-e912246b9dfc","resolution":{"observed_at":"2026-08-03T10:56:16.020021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.21079","last_updated":"2025-02-28T14:11:20Z","snapshot_observed_at":"2026-08-07T17:39:41.540184Z","submitted_at":"2025-02-28T14:11:20Z","title":"Training-free and Adaptive Sparse Attention for Efficient Long Video Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.21079","snapshot_observed_at":"2026-08-03T10:56:16.089882Z","title":"Training-free and adaptive sparse attention for efficient long video generation.arXiv preprint arXiv:2502.21079, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.089882Z"},"links":{"cited_paper":"/paper/2502.21079","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:60f3522e44960d1741982058b4c6547510e2fbaa324ee056ab8bbffa98d6942a","observation_id":"006c6c8e-48ee-47e2-ad60-03f549ee9556","resolution":{"observed_at":"2026-08-03T10:56:16.089882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:16.149827Z","title":"SANA: Efficient high-resolution text-to-image synthesis with linear diffusion transformers","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.149827Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:6d14d505c0ad3d5004dcae28e4b5df4eb8e8aa31126054b183d2dd10f715f625","observation_id":"485b0ef3-815e-4571-bbda-c9f75378e010","resolution":{"observed_at":"2026-08-03T10:56:16.149827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:16.169796Z","title":"Ufogen: You forward once large scale text-to-image gener- ation via diffusion gans","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.169796Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:da23ae029921731a3df7ec872d90cd3116b74c01ebe9a6572ded43ede0b04aff","observation_id":"b37975ae-3281-441c-a100-7918d1426264","resolution":{"observed_at":"2026-08-03T10:56:16.169796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14867","last_updated":"2024-05-24T17:08:32Z","snapshot_observed_at":"2026-08-12T23:59:30.187265Z","submitted_at":"2024-05-23T17:59:49Z","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14867","snapshot_observed_at":"2026-08-03T10:56:16.227824Z","title":"Im- proved distribution matching distillation for fast image syn- thesis.arXiv preprint arXiv:2405.14867, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.227824Z"},"links":{"cited_paper":"/paper/2405.14867","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:9179426ef3a5530bf8aaaacb5cee83a477d913926d9a1defc0ae88a07c421005","observation_id":"c0eee8f9-0d62-4ea1-a04f-16bd6b472d36","resolution":{"observed_at":"2026-08-03T10:56:16.227824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:16.284414Z","title":"One-step diffusion with distribution matching distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.284414Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:c5b136371048a8a41133d5ef0da3b9a64cc513cdc4dfc2bca745290f40a59017","observation_id":"24a269b7-472a-4d4b-9d4e-7ac6515ce4fe","resolution":{"observed_at":"2026-08-03T10:56:16.284414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:16.341129Z","title":"From slow bidirectional to fast autoregressive video diffusion mod- els","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.341129Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:76ec3cb0539c5908f0e848a15d2594ba80ac57b8d21992b36735efaf4510fd70","observation_id":"b29f6fd5-d43d-4350-9a04-d3c652322061","resolution":{"observed_at":"2026-08-03T10:56:16.341129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:16.447992Z","title":"Slimmable neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.447992Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:4061496bde17fdb98f1325a152d5b5c6f4e66b660b5431e22056fc6e9859cb61","observation_id":"238be2b0-f902-4817-a337-11ebca40075b","resolution":{"observed_at":"2026-08-03T10:56:16.447992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:16.576532Z","title":"Scaling autoregressive models for content-rich text-to-image generation.Transactions on Machine Learn- ing Research, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.576532Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:b5d9b7076dce81fbdad50664032757305c72192679e6a258308e63fc478ebf23","observation_id":"31e9335b-f970-4f8d-b1ac-271d6d503646","resolution":{"observed_at":"2026-08-03T10:56:16.576532Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11089","last_updated":"2025-02-27T09:01:21Z","snapshot_observed_at":"2026-08-07T14:17:15.942844Z","submitted_at":"2025-02-16T11:53:44Z","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11089","snapshot_observed_at":"2026-08-03T10:56:16.689723Z","title":"Native sparse at- tention: Hardware-aligned and natively trainable sparse at- tention.arXiv preprint arXiv:2502.11089, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.689723Z"},"links":{"cited_paper":"/paper/2502.11089","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:e334047245f7a40a91208ff847206a1f8fac82f57dcc215451381220526cb720","observation_id":"dc798911-ed13-4c54-973b-ea2b99f76364","resolution":{"observed_at":"2026-08-03T10:56:16.689723Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04507","last_updated":"2025-06-04T23:21:39Z","snapshot_observed_at":"2026-08-12T05:38:58.830320Z","submitted_at":"2025-02-06T21:17:09Z","title":"Fast Video Generation with Sliding Tile Attention","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04507","snapshot_observed_at":"2026-08-03T10:56:16.762692Z","title":"Fast video generation with sliding tile attention.arXiv preprint arXiv:2502.04507, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.762692Z"},"links":{"cited_paper":"/paper/2502.04507","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:fa47eddeb1c8310b5f85db58cded93302f374ed237a705838a36a6d4b11de446","observation_id":"4b067793-9d51-4262-b399-3fea5702ea10","resolution":{"observed_at":"2026-08-03T10:56:16.762692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16567","last_updated":"2024-06-12T07:16:21Z","snapshot_observed_at":"2026-08-13T05:15:41.214822Z","submitted_at":"2023-11-28T07:14:41Z","title":"MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16567","snapshot_observed_at":"2026-08-03T10:56:16.907915Z","title":"Mobilediffusion: Subsecond text-to-image generation on mobile devices.arXiv preprint arXiv:2311.16567, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:16.907915Z"},"links":{"cited_paper":"/paper/2311.16567","citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:1da23377fe799331394e21ea90ea3cb064113f783816dc77e2b56aee20ca2968","observation_id":"4cc6e522-81ed-4a76-baec-ef4369aff215","resolution":{"observed_at":"2026-08-03T10:56:16.907915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:56:17.053263Z","title":"Generate","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-03T10:56:17.053263Z"},"links":{"citing_paper":"/paper/2601.08303"},"observation_digest":"sha256:1d86a7312c3076e97ac8607d5a4b1c266492c8f0cc1c498a9bda73ed3b586f22","observation_id":"b970f782-34d1-4a5d-b8de-a2e041ab0961","resolution":{"observed_at":"2026-08-03T10:56:17.053263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.08303","last_updated":"2026-07-06T07:20:34Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T13:59:11.336528Z","submitted_at":"2026-01-13T07:46:46Z","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices"},"reference_resolution":{"displayed":86,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":86,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":86},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 1 inbound Pith citation observation for arXiv:2601.08303."}