{"as_of":"2026-08-13T18:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0f5ce3f54bc5fd2c485cbf4a42f4fdc9b38cae200ff31de052e407b81c89e811","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:07:10.387517Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.00759/citation-record","integrity":"/paper/2412.00759/integrity","json":"/paper/2412.00759/citation-record.json","paper":"/paper/2412.00759"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-12T05:07:10.104955Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.104955Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:fc03f9585ad929caa3613e0e973cb81458d44a3d1c3a81dc711c2140787b5918","observation_id":"21c58512-10a9-420c-8d74-1edd75c91538","resolution":{"observed_at":"2026-08-12T05:07:10.104955Z","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":"2026-08-12T05:07:10.112687Z","title":"Universal guidance for diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.112687Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:4a1cb26b8cdeca2e516455cef7dda40b0640f6be495dd58b5c15e3d192755a55","observation_id":"558f238f-3e8c-46a7-9083-5a05116e010d","resolution":{"observed_at":"2026-08-12T05:07:10.112687Z","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":"2026-08-12T05:07:10.118369Z","title":"Improving image generation with better captions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.118369Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:1fc53cd7453f742e97c23f70f7d76d93ffe593e21646017d7477d798ac844e8d","observation_id":"aa4f1ffb-0d90-4433-98ad-7e492dd40534","resolution":{"observed_at":"2026-08-12T05:07:10.118369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13301","last_updated":"2024-01-04T19:11:25Z","snapshot_observed_at":"2026-08-09T16:20:23.732146Z","submitted_at":"2023-05-22T17:57:41Z","title":"Training Diffusion Models with Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13301","snapshot_observed_at":"2026-08-12T05:07:10.123479Z","title":"Training diffusion models with reinforce- ment learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.123479Z"},"links":{"cited_paper":"/paper/2305.13301","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:8eb0a1c9bb7147b4eb049b280601f9239b9486c9ea188fec36b19a585137215d","observation_id":"0ff43ef4-44f2-418f-95c8-6b930cc959eb","resolution":{"observed_at":"2026-08-12T05:07:10.123479Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.552531Z","title":"Solving 3d inverse problems using pre-trained 2d diffusion models","venue":null,"work_id":"ab020755-16d4-4488-8b4c-66dbdd7cee47","year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.128521Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:7a74652caf188ae7cde0662fedb5e052f0534c91515cd9d30036f3809617f150","observation_id":"00313deb-c7fe-4c93-8ed7-fc254bf30e81","resolution":{"observed_at":"2026-08-12T05:07:11.557623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17400","last_updated":"2024-06-21T16:45:11Z","snapshot_observed_at":"2026-08-06T10:08:54.816113Z","submitted_at":"2023-09-29T17:01:02Z","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17400","snapshot_observed_at":"2026-08-12T05:07:10.133850Z","title":"Directly fine-tuning diffusion models on differentiable re- wards","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.133850Z"},"links":{"cited_paper":"/paper/2309.17400","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:eaa94f31c08e4bee6e91c5a83533e0bbac59979c222153ccfd0ad0eebe966169","observation_id":"51ee30d8-acdf-4952-b3ff-bd26933b7143","resolution":{"observed_at":"2026-08-12T05:07:10.133850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12059","last_updated":"2024-06-22T16:58:19Z","snapshot_observed_at":"2026-08-13T10:29:07.124871Z","submitted_at":"2023-08-23T10:59:41Z","title":"Manipulating Embeddings of Stable Diffusion Prompts","version":2},"cited_work":{"arxiv_id":"2308.12059","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.12059","snapshot_observed_at":"2026-08-12T05:07:10.909045Z","title":"Manipulating Embeddings of Stable Diffusion Prompts","venue":"cs.CV","work_id":"9562934f-1619-4277-9f1c-d43f926b8186","year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.139082Z"},"links":{"cited_paper":"/paper/2308.12059","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:cbd89f3899b73143d2f6c5734f4db25416cad60521aaea94ac9c9edfca71c129","observation_id":"3f09d32a-f7c1-4948-a10c-f3c8334ed289","resolution":{"observed_at":"2026-08-12T05:07:10.920207Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:10.143997Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.143997Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:72de69bf24a9d0594c00af1a5989bdebdf260dc178ea31c2e6fff7cfcd845474","observation_id":"b2750a26-257d-40a9-b9fa-3d41c61ad386","resolution":{"observed_at":"2026-08-12T05:07:10.143997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06767","last_updated":"2023-12-01T14:28:06Z","snapshot_observed_at":"2026-08-07T04:02:54.504761Z","submitted_at":"2023-04-13T18:22:40Z","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06767","snapshot_observed_at":"2026-08-12T05:07:10.149405Z","title":"Raft: Reward ranked finetuning for generative foundation model alignment","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.149405Z"},"links":{"cited_paper":"/paper/2304.06767","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:6c82727766b155272d14eb3df30bf39254d273e248220f17a5b63153bd6baa74","observation_id":"86e602d3-9e5e-45ab-b91a-f04ec441352f","resolution":{"observed_at":"2026-08-12T05:07:10.149405Z","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":"2026-08-12T05:07:10.154151Z","title":"Scaling recti- fied flow transformers for high-resolution image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.154151Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:bc1e77030066c8944c3cd8115d1e67fb28d5cb56fa897e1bafde0a616a3554b5","observation_id":"f41507a8-062d-4efe-8a3b-222cb4df835a","resolution":{"observed_at":"2026-08-12T05:07:10.154151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04312","last_updated":"2024-10-31T17:47:54Z","snapshot_observed_at":"2026-08-12T23:48:30.417654Z","submitted_at":"2024-06-06T17:56:40Z","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04312","snapshot_observed_at":"2026-08-12T05:07:10.158667Z","title":"Reno: Enhancing one-step text-to-image models through reward-based noise optimiza- tion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.158667Z"},"links":{"cited_paper":"/paper/2406.04312","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:6ecb906dab6473fb3f98a98e83c714e942d997b8da9ee548e0bbcfa7f3481d8b","observation_id":"fe2d5d03-9342-4d2a-84d1-fbded927de97","resolution":{"observed_at":"2026-08-12T05:07:10.158667Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.515372Z","title":"Re- inforcement learning for fine-tuning text-to-image diffusion models","venue":null,"work_id":"8ef8b230-473a-4d04-a484-28f70cb5c032","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.163769Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:103a21f597176c4c6177c8805cb4393f0c0527e16022298623cd03e0c11bd277","observation_id":"53221506-11db-45d9-b969-87b8c1e70f35","resolution":{"observed_at":"2026-08-12T05:07:11.520924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:10.168555Z","title":"Aligning diffusion models with noise- conditioned perception","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.168555Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:997f2f6cd6b8643da7f21471eb18cea4a6095479f8aac89a168e1496564b9025","observation_id":"dc70493b-20eb-4328-9b0e-a4fa9baa1aa6","resolution":{"observed_at":"2026-08-12T05:07:10.168555Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.498883Z","title":"Geneval: An object-focused framework for evaluating text- to-image alignment","venue":null,"work_id":"95b615fd-9769-42bf-8fd2-53747c124985","year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.173059Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:9800a3f9e5451109c76e595cf3d768e85a91305619a2103bcc17ff45bf6e4a8a","observation_id":"27f61534-32a3-41ac-9db9-7b50689f3c27","resolution":{"observed_at":"2026-08-12T05:07:11.504768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06382","last_updated":"2024-06-10T15:42:03Z","snapshot_observed_at":"2026-08-12T23:46:21.915932Z","submitted_at":"2024-06-10T15:42:03Z","title":"Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06382","snapshot_observed_at":"2026-08-12T05:07:10.177735Z","title":"Diffusion-rpo: Aligning diffusion mod- els through relative preference optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.177735Z"},"links":{"cited_paper":"/paper/2406.06382","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:7ad71930d5a1f8ada91fab9ad5cbc35e6b38b0b8684bb70919c27f5a28a8292c","observation_id":"bceac320-9a14-4cae-aef3-b4acaae86723","resolution":{"observed_at":"2026-08-12T05:07:10.177735Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.482817Z","title":"Initno: Boosting text-to-image diffu- sion models via initial noise optimization","venue":null,"work_id":"aa55cb5b-6dff-4f21-86be-c50895df284f","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.182446Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:bdaf9bf49c8871957d131be42d3f28aa57bd61eb029c9263cd0c2e214393984f","observation_id":"c954e939-f757-470d-87e6-f113fd1ba4cb","resolution":{"observed_at":"2026-08-12T05:07:11.487744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01626","last_updated":"2022-08-02T17:55:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-08-02T17:55:41Z","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01626","snapshot_observed_at":"2026-08-12T05:07:10.187198Z","title":"Prompt-to-prompt im- age editing with cross attention control","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.187198Z"},"links":{"cited_paper":"/paper/2208.01626","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:861e8331294e5b7a175ac80e4665f3714fbd71d7fae358984afc9630a2315d0e","observation_id":"f3051112-1de9-4446-adc5-c0262c4bc2ff","resolution":{"observed_at":"2026-08-12T05:07:10.187198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-08-12T19:28:23.372660Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-12T05:07:10.192114Z","title":"Classifier-free diffusion guidance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.192114Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:ce1a49af69cb9f4b7f6f9560d7fbb487407ee728ee1ca0c8a2b2381e6d7d0be3","observation_id":"58485b3e-7bcb-4159-aadd-35c1af56e9c7","resolution":{"observed_at":"2026-08-12T05:07:10.192114Z","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":"2026-08-12T05:07:10.196752Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.196752Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:85285a00d40f221fce48006e12bd2ad462271e82819270aa23e60e0b222d2d4c","observation_id":"831f26f7-f341-4b4e-8d65-39db8e669411","resolution":{"observed_at":"2026-08-12T05:07:10.196752Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.455131Z","title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","venue":null,"work_id":"bae18d63-7718-4956-86b3-57caa7bcd81d","year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.201121Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:85eb11cad15994ecc87fc1305b8ad3550de883f2d2f28c3d626134f2b2189004","observation_id":"70c8d752-eade-472b-982e-d771f7e675c3","resolution":{"observed_at":"2026-08-12T05:07:11.460821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.439671Z","title":"Flux.1-schnell, 2024","venue":null,"work_id":"d241d9f1-c7e1-454b-a7a7-7bc3f1bd11a4","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.205950Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:591f7201bc146604acdb9a158601abc8235c7df700550ce960c08839b365c63f","observation_id":"77904706-8ea2-4912-b19f-9921fdb0d00b","resolution":{"observed_at":"2026-08-12T05:07:11.444063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12192","last_updated":"2023-02-23T17:34:53Z","snapshot_observed_at":"2026-07-06T14:55:12.100148Z","submitted_at":"2023-02-23T17:34:53Z","title":"Aligning Text-to-Image Models using Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12192","snapshot_observed_at":"2026-08-12T05:07:10.210697Z","title":"Aligning text- to-image models using human feedback","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.210697Z"},"links":{"cited_paper":"/paper/2302.12192","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:41798e1a5bb148d8a09c6fb28cea60474d85dbd0c013bd1c4e6a71222cd46a14","observation_id":"0757cc70-4749-4a7c-99af-8f3ae76dc145","resolution":{"observed_at":"2026-08-12T05:07:10.210697Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.04465","last_updated":"2024-10-11T19:43:11Z","snapshot_observed_at":"2026-08-13T00:36:44.636118Z","submitted_at":"2024-04-06T01:23:23Z","title":"Aligning Diffusion Models by Optimizing Human Utility","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.04465","snapshot_observed_at":"2026-08-12T05:07:10.215733Z","title":"Aligning diffusion models by optimizing human utility","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.215733Z"},"links":{"cited_paper":"/paper/2404.04465","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:e68a18e30b6e148db77ba7f48e6c7d30a43c3428d7a66b15bd3babe1d1b1175d","observation_id":"e1e8df4a-4342-4e8f-bf1c-591f4e6a67fd","resolution":{"observed_at":"2026-08-12T05:07:10.215733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04314","last_updated":"2025-03-25T17:06:27Z","snapshot_observed_at":"2026-08-12T23:48:30.414248Z","submitted_at":"2024-06-06T17:57:09Z","title":"Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04314","snapshot_observed_at":"2026-08-12T05:07:10.220766Z","title":"Step-aware prefer- ence optimization: Aligning preference with denoising per- formance at each step","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.220766Z"},"links":{"cited_paper":"/paper/2406.04314","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:ef5e496981639c4b518796bc5db46729666f4996f2822054b083279add51c2e1","observation_id":"42cd921c-f1a5-4cb0-8719-2f6b19bc37c3","resolution":{"observed_at":"2026-08-12T05:07:10.220766Z","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":"2026-08-12T05:07:10.226169Z","title":"Alignment of dif- fusion models: Fundamentals, challenges, and future","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.226169Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:ca7eb6bfcfabbe1a2c33e4a26080944aeada22004082ece355d4626ab467cb43","observation_id":"7768dee2-c2a4-486e-b07a-ec7c17a1b7e5","resolution":{"observed_at":"2026-08-12T05:07:10.226169Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.423255Z","title":"More control for free! im- age synthesis with semantic diffusion guidance","venue":null,"work_id":"0fd10cfe-6c7e-4925-be11-d59ca32dc955","year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.230668Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:a5c776b6c088b5d47476cbce92d4f34ec0ae28b547ca92751beeb91c9907622a","observation_id":"6862f4f4-0378-4648-a3ab-8d03d13861d3","resolution":{"observed_at":"2026-08-12T05:07:11.428777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02549","last_updated":"2024-06-04T17:59:32Z","snapshot_observed_at":"2026-08-12T23:50:15.040473Z","submitted_at":"2024-06-04T17:59:32Z","title":"Dreamguider: Improved Training free Diffusion-based Conditional Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02549","snapshot_observed_at":"2026-08-12T05:07:10.235579Z","title":"Dreamguider: Improved training free diffusion-based conditional generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.235579Z"},"links":{"cited_paper":"/paper/2406.02549","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:b0d23855f422cf6498db9c4dc98baeb37395b9b95490ba65a22f5018b0a2ee28","observation_id":"d945acab-6e62-46f4-8aa6-6ecd663813c7","resolution":{"observed_at":"2026-08-12T05:07:10.235579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10741","last_updated":"2022-03-08T18:18:49Z","snapshot_observed_at":"2026-08-07T12:21:17.790675Z","submitted_at":"2021-12-20T18:42:55Z","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10741","snapshot_observed_at":"2026-08-12T05:07:10.240590Z","title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models.arXiv preprint arXiv:2112.10741, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.240590Z"},"links":{"cited_paper":"/paper/2112.10741","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:4e8dd448a6860b2e512e726a952b8ff7c6c7ea5854bb7316b56a762a8e550afd","observation_id":"87dd58d1-62db-4fa1-8f61-aaa5653260e9","resolution":{"observed_at":"2026-08-12T05:07:10.240590Z","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":"2026-08-12T05:07:10.245027Z","title":"Sdxl: Improving latent diffusion mod- els for high-resolution image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.245027Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:c04b02aa1f2399ff405bb18d2b711e00a22d08dad9ee89a8676f8d722488be42","observation_id":"7afa36a0-2a4c-4917-aa8f-802f0853fd4c","resolution":{"observed_at":"2026-08-12T05:07:10.245027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03739","last_updated":"2024-11-07T03:54:22Z","snapshot_observed_at":"2026-07-06T16:28:22.350574Z","submitted_at":"2023-10-05T17:59:18Z","title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03739","snapshot_observed_at":"2026-08-12T05:07:10.250604Z","title":"Aligning text-to-image diffusion models with reward backpropagation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.250604Z"},"links":{"cited_paper":"/paper/2310.03739","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:6d1e4950a5f410a339fa7393f59a22b6abd5829fbd7a6cab15ea2cf9e2088936","observation_id":"aaaf1a53-e6b0-4bbb-8d05-452d6995d1ac","resolution":{"observed_at":"2026-08-12T05:07:10.250604Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.406668Z","title":"Direct preference optimization: Your language model is secretly a reward model","venue":null,"work_id":"94bc5cf0-af40-4347-ad0a-9a4c4cd9be16","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.255733Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:82ef208e01b98645884e1e98acbbd837530533dc33fa6564f5233a1803364bae","observation_id":"035a4c45-1541-4ec0-b65f-c43cfdf8ce0a","resolution":{"observed_at":"2026-08-12T05:07:11.412111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.386408Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"cc4cde2f-3f2c-4b13-b543-ef93b44ce4b5","year":2022},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.260770Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:eea9c13222476f60b43ebf648cec953b7a54fd27a52f1c36fcb3bc38b9cf6ac7","observation_id":"0682d329-e124-40cd-8ca6-4a0a4a3b5c31","resolution":{"observed_at":"2026-08-12T05:07:11.394673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:10.265538Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.265538Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:0e70ff74f6a252eb3b35933a41a749394fac3b536e1a531f88cd8953184d6932","observation_id":"b896313c-069f-427b-bcba-2b00fbe40eac","resolution":{"observed_at":"2026-08-12T05:07:10.265538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12015","last_updated":"2024-03-18T17:51:43Z","snapshot_observed_at":"2026-08-13T00:51:01.462454Z","submitted_at":"2024-03-18T17:51:43Z","title":"Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12015","snapshot_observed_at":"2026-08-12T05:07:10.270046Z","title":"Fast high- resolution image synthesis with latent adversarial diffusion distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.270046Z"},"links":{"cited_paper":"/paper/2403.12015","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:bd64d7d6762c793406508f709a43ba16ce65b2fe9b10cd3fc469c2649f40b733","observation_id":"03622e32-6d97-4bc7-a543-4fff84314202","resolution":{"observed_at":"2026-08-12T05:07:10.270046Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.242026Z","title":"Laion-aesthetics","venue":null,"work_id":"5dc793cb-b8dd-406d-8d46-40dff66feab9","year":2022},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.274645Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:69bcfe7b97b85bb0dfff54ca94c8f979cbaeba00d6bbcd575bac302adb3b2eb0","observation_id":"a58141e2-e62b-428c-82a6-83efa5447144","resolution":{"observed_at":"2026-08-12T05:07:11.247608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.226572Z","title":"Understanding and improv- ing training-free loss-based diffusion guidance, 2024","venue":null,"work_id":"bc254a53-a4e8-40d5-ad3a-322b60e674c9","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.279214Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:5fa8b41384a611806d3e08474c2883830635d443f7a52ade1e66d532f74e883c","observation_id":"2ef6c14d-9ec0-47c1-81be-b2996b0aac44","resolution":{"observed_at":"2026-08-12T05:07:11.231708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.208870Z","title":"Pseudoinverse-guided diffusion models for inverse problems","venue":null,"work_id":"515bd53b-7ad1-4523-9251-61aa1b7a5cab","year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.283688Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:e742ce303f7657c7cb6e591bed6dbc015bed8472e4f9ed54a6b2b2c40ca6a6ff","observation_id":"6d6fa47e-8cd6-4e78-ba74-8c12206db9f0","resolution":{"observed_at":"2026-08-12T05:07:11.214620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:10.288059Z","title":"Generative modeling by esti- mating gradients of the data distribution","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.288059Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:4f403756c33d7a4e8af373a096e5b4cfc5b0913d9a771a9799666fdf5a8066b7","observation_id":"666cd948-074b-407f-92a2-aa88122e7a07","resolution":{"observed_at":"2026-08-12T05:07:10.288059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-12T05:07:10.292471Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.292471Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:b4c9a7d4ac422763b2fe60f85c13d1c3f146dcdc8673158783d5c2f43ccdf327","observation_id":"49856bfd-a305-431b-9953-de05d2357b48","resolution":{"observed_at":"2026-08-12T05:07:10.292471Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.181821Z","title":"Eggen: Image genera- tion with multi-entity prior learning through entity guidance","venue":null,"work_id":"67316784-83ae-45bd-9a58-c07eb9d0aabc","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.297025Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:0655992f8d638fd534099aa67be8fa2465cff560008c0ea8e105b70c2f180e99","observation_id":"22497c2e-f6c9-4eec-87d6-a48c7173936c","resolution":{"observed_at":"2026-08-12T05:07:11.188145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.18881","last_updated":"2024-10-02T05:22:07Z","snapshot_observed_at":"2026-08-12T23:55:24.883811Z","submitted_at":"2024-05-29T08:39:39Z","title":"Inference-Time Alignment of Diffusion Models with Direct Noise Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18881","snapshot_observed_at":"2026-08-12T05:07:10.301600Z","title":"Tuning-free align- ment of diffusion models with direct noise optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.301600Z"},"links":{"cited_paper":"/paper/2405.18881","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:4613b5187b1f5460ea6b9e5befd98993e175d0e36cc44d15f5ea32f967f9eb38","observation_id":"85f1edf8-c06c-4c1f-84c1-0eebf6001384","resolution":{"observed_at":"2026-08-12T05:07:10.301600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-12T05:07:10.306360Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.306360Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:6adedf049d629c0a6d57267de4b94aac1ed308bcd234f79d3821aa6df981a9bb","observation_id":"f78cf440-ed51-42b9-8696-c9e49dc09228","resolution":{"observed_at":"2026-08-12T05:07:10.306360Z","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":"2026-08-12T05:07:10.310588Z","title":"Plug-and-play diffusion features for text-driven image-to-image translation","venue":null,"work_id":null,"year":1921},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.310588Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:7bab85d35ba2c8468bd064a2cec39a042ed9532d5e4c1736bd630112a7c117ca","observation_id":"d8eada6a-2789-4729-a420-fa57f1bfd5af","resolution":{"observed_at":"2026-08-12T05:07:10.310588Z","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":"2026-08-12T05:07:10.314870Z","title":"End-to-end diffusion latent optimization improves classifier guidance","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.314870Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:d9f98fdde2662cfaf8f04875e0f3b56ccbb096a7c53196241b340ac6f1b8812d","observation_id":"439ee8c6-2d84-4608-8cd7-04c8bf117df0","resolution":{"observed_at":"2026-08-12T05:07:10.314870Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.146424Z","title":"Diffusion model align- ment using direct preference optimization","venue":null,"work_id":"24342310-5c7b-49d6-b23a-6dcbde45cdc4","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.319897Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:1672435e2d207ab98142a8e8be7143ab76dd67b37ac9cdaed4dffbd1b2dc979a","observation_id":"50f8d2ef-7b06-471f-ad1a-f548e6db3cbc","resolution":{"observed_at":"2026-08-12T05:07:11.151853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.130400Z","title":"Magic: Multi-modality guided image completion","venue":null,"work_id":"988e8e41-f6bf-4c06-8289-78a1ac087cb7","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.324613Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:008825a8e2c02d53f28ff8213a4a533ff76fe0111088539d8489cefcc90bf6c8","observation_id":"813d95bb-365c-4861-80b2-afae4279936a","resolution":{"observed_at":"2026-08-12T05:07:11.136179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09341","last_updated":"2023-09-25T08:19:23Z","snapshot_observed_at":"2026-08-13T09:05:45.892435Z","submitted_at":"2023-06-15T17:59:31Z","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09341","snapshot_observed_at":"2026-08-12T05:07:10.328889Z","title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.328889Z"},"links":{"cited_paper":"/paper/2306.09341","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:2035714401e207dff4dd6667b4dd4cde0c2c28ffec47a3241e3a603f9b2d0c8b","observation_id":"d1353ad2-71a7-414c-97dd-b9e1c070aaf8","resolution":{"observed_at":"2026-08-12T05:07:10.328889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00760","last_updated":"2024-05-01T15:26:14Z","snapshot_observed_at":"2026-08-13T00:17:34.790360Z","submitted_at":"2024-05-01T15:26:14Z","title":"Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00760","snapshot_observed_at":"2026-08-12T05:07:10.333423Z","title":"Deep reward supervisions for tuning text-to-image diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.333423Z"},"links":{"cited_paper":"/paper/2405.00760","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:951cd6841e61e8510bbb29ec9121810c510196debe5ca4f81d5a229c6e02e2d3","observation_id":"0f8c3799-1d69-4428-af84-f03b07e2d08d","resolution":{"observed_at":"2026-08-12T05:07:10.333423Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.114701Z","title":"Imagere- ward: Learning and evaluating human preferences for text- to-image generation","venue":null,"work_id":"4ba6ea60-ebb5-4cad-806d-f1e461f707de","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.338314Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:eb57d7c98c77c8954534dae5257014fbe243228bc29ba8773dc6afe3161ec1af","observation_id":"e2327fc3-4612-4f32-b17e-68abbb1cbbb0","resolution":{"observed_at":"2026-08-12T05:07:11.119917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.099385Z","title":"Using human feedback to fine-tune diffusion models without any reward model","venue":null,"work_id":"38f2d7c2-e054-4f9a-b6b0-4935acd65b82","year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.342684Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:158ad93ae1e3752ee06c19d35e83f78c76c600b5bd7dfaaf278045716ddd6977","observation_id":"da4d41bf-3b80-4a68-a6a9-6442fbdd4524","resolution":{"observed_at":"2026-08-12T05:07:11.104383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08265","last_updated":"2024-05-12T21:02:59Z","snapshot_observed_at":"2026-08-13T04:20:02.456002Z","submitted_at":"2024-02-13T07:37:24Z","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08265","snapshot_observed_at":"2026-08-12T05:07:10.346800Z","title":"A dense reward view on aligning text-to-image diffusion with prefer- ence","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.346800Z"},"links":{"cited_paper":"/paper/2402.08265","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:de5c0e6a1eee4aafb206fa6ab40c1a37eb427433b805b94c561a15822d9c5879","observation_id":"b2a36008-adb1-4db6-9ced-3b4bc916eab7","resolution":{"observed_at":"2026-08-12T05:07:10.346800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.15761","last_updated":"2024-11-19T08:12:46Z","snapshot_observed_at":"2026-08-12T22:38:58.259196Z","submitted_at":"2024-09-24T05:31:17Z","title":"TFG: Unified Training-Free Guidance for Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.15761","snapshot_observed_at":"2026-08-12T05:07:10.351358Z","title":"Tfg: Unified training-free guidance for diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.351358Z"},"links":{"cited_paper":"/paper/2409.15761","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:ee9a81e06cd7b5634777716886b3366a4b395a84da021095be91e3ae9a26d975","observation_id":"e29efa5c-0d66-4fe1-90a1-c057709edb2c","resolution":{"observed_at":"2026-08-12T05:07:10.351358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10789","last_updated":"2022-06-22T01:11:29Z","snapshot_observed_at":"2026-08-13T13:45:12.888881Z","submitted_at":"2022-06-22T01:11:29Z","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10789","snapshot_observed_at":"2026-08-12T05:07:10.355770Z","title":"Scaling autoregres- sive models for content-rich text-to-image generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.355770Z"},"links":{"cited_paper":"/paper/2206.10789","citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:3e758ff69ee67a9663b3d087abdeb06bb0407cf9744ea4528c6f00e2fd976308","observation_id":"1108ca6b-a331-4646-bd7e-017103ddbdaf","resolution":{"observed_at":"2026-08-12T05:07:10.355770Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.083595Z","title":"Freedom: Training-free energy-guided condi- tional diffusion model","venue":null,"work_id":"b88d2e35-8e3f-44dc-b6d0-4b44f83d1a08","year":2023},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.361047Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:cf2a121dc47d09114e6cc81fe182d6c890e32973946241f1457edb6015ca652c","observation_id":"b1d03871-ea8c-4bf6-afff-a5deb6d7c209","resolution":{"observed_at":"2026-08-12T05:07:11.089156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.067261Z","title":"Object- conditioned energy-based attention map alignment in text-to- image diffusion models","venue":null,"work_id":"f8f933bf-9cc4-4268-8abc-e80d81d69bfb","year":2025},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.365316Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:a16e38effa8a804353eddea8801a0a72e4b2a217a3dfc88b30a118d8eda4831c","observation_id":"06eedd97-047f-4638-83db-d9956045d96f","resolution":{"observed_at":"2026-08-12T05:07:11.072478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.050248Z","title":"Differentiable augmentation for data-efficient gan training","venue":null,"work_id":"c4bfe83a-1db9-4d2c-a386-3b1f62747776","year":2020},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.369559Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:6696461bd555ad927bb4ffb69559fc780a8e94465c45adc4a4222defc17ef51d","observation_id":"58fed634-d100-4d1a-a92d-4b09ba1d767f","resolution":{"observed_at":"2026-08-12T05:07:11.055824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.034426Z","title":null,"venue":null,"work_id":"a73d2d03-eecc-4939-9bec-e675c477d1f1","year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.374245Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:b9b5abf78cef93108050aa0f11778fc1c8f25891a2aaee6cdbd63bd46793d459","observation_id":"0233c7dc-c76f-4770-bc5b-78be9e2c420b","resolution":{"observed_at":"2026-08-12T05:07:11.039276Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:11.016202Z","title":"Details of Prompts used in Experiments The text prompts used to generate the images in Fig","venue":null,"work_id":"5c596b42-b085-431c-9306-d625f91742af","year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.378613Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:f8ba184340a8438a01591f65e3aa1e7771a586a866d8fb76cc3bb1c1f4674f12","observation_id":"b1254319-6cb7-4fec-99fd-a65bc63ab174","resolution":{"observed_at":"2026-08-12T05:07:11.021961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:10.999227Z","title":null,"venue":null,"work_id":"a97a2c9f-3894-4f06-b902-db7156476499","year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.383037Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:de5330cee01e58ab60e2501fd2c4111d89df0ab1950cc7be6e2210a53ff152c7","observation_id":"d959df94-3bd1-4ec0-8694-70d7c10785a5","resolution":{"observed_at":"2026-08-12T05:07:11.004782Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:07:10.981029Z","title":"prompt\":","venue":null,"work_id":"37287770-91b0-4376-9491-821c5ebb4eff","year":null},"citing_paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T05:07:10.387517Z"},"links":{"citing_paper":"/paper/2412.00759"},"observation_digest":"sha256:e494a5774411ad99e51eaa92ecd21dc80df2a141618fff21646862a7081282d0","observation_id":"510730c2-3a60-4817-ac36-c1edfe5e060c","resolution":{"observed_at":"2026-08-12T05:07:10.988638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.00759","last_updated":"2025-03-25T08:53:39Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T08:50:03.241069Z","submitted_at":"2024-12-01T10:32:47Z","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":37,"verified_exact":1,"verified_fuzzy":22},"total_outbound_references":60},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2412.00759."}