{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KOB76DQGQWWYD6NUFINVJR3PQJ","short_pith_number":"pith:KOB76DQG","schema_version":"1.0","canonical_sha256":"5383ff0e0685ad81f9b42a1b54c76f827531ac59f0eb81ea3c8ea42ed297ae81","source":{"kind":"arxiv","id":"2406.02540","version":3},"attestation_state":"computed","paper":{"title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enshu Liu, Guohao Dai, Haofeng Huang, Huazhong Yang, Rui Wan, Shengen Yan, Shiyao Li, Tianchen Zhao, Tongcheng Fang, Widyadewi Soedarmadji, Xuefei Ning, Yu Wang, Zinan Lin","submitted_at":"2024-06-04T17:57:10Z","abstract_excerpt":"Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video generation lead to increased computational and memory costs, posing challenges for practical deployment on edge devices. Post-Training Quantization (PTQ) is an effective method for reducing memory costs and computational complexity. When quantizing diffusion transformers, we find that existing quantization methods face challenges when applied to text-to-image and "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.02540","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T17:57:10Z","cross_cats_sorted":[],"title_canon_sha256":"872d92eef515f606175e8cc59530fd2f8cb773d83cf02a376cbe7e42daf599df","abstract_canon_sha256":"77f0b8b1f2ad8a8b00589fac2c9173fc846396a72d946b61f664fb5b7f9c843e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:08.738535Z","signature_b64":"JH5f0pBByP05j7+j++P291FSdFhB3p6l2K0z8qHHJRx5AqZgY9BdIdoW0fzh6XLAufbiceX4WgGcLzemwRvfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5383ff0e0685ad81f9b42a1b54c76f827531ac59f0eb81ea3c8ea42ed297ae81","last_reissued_at":"2026-07-05T10:18:08.738034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:08.738034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enshu Liu, Guohao Dai, Haofeng Huang, Huazhong Yang, Rui Wan, Shengen Yan, Shiyao Li, Tianchen Zhao, Tongcheng Fang, Widyadewi Soedarmadji, Xuefei Ning, Yu Wang, Zinan Lin","submitted_at":"2024-06-04T17:57:10Z","abstract_excerpt":"Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video generation lead to increased computational and memory costs, posing challenges for practical deployment on edge devices. Post-Training Quantization (PTQ) is an effective method for reducing memory costs and computational complexity. When quantizing diffusion transformers, we find that existing quantization methods face challenges when applied to text-to-image and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02540","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.02540/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.02540","created_at":"2026-07-05T10:18:08.738097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02540v3","created_at":"2026-07-05T10:18:08.738097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02540","created_at":"2026-07-05T10:18:08.738097+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOB76DQGQWWY","created_at":"2026-07-05T10:18:08.738097+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOB76DQGQWWYD6NU","created_at":"2026-07-05T10:18:08.738097+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOB76DQG","created_at":"2026-07-05T10:18:08.738097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17800","citing_title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02461","citing_title":"OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12280","citing_title":"Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06060","citing_title":"ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28803","citing_title":"{\\Omega}-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18739","citing_title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20309","citing_title":"QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01725","citing_title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14513","citing_title":"HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01725","citing_title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":193,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ","json":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ.json","graph_json":"https://pith.science/api/pith-number/KOB76DQGQWWYD6NUFINVJR3PQJ/graph.json","events_json":"https://pith.science/api/pith-number/KOB76DQGQWWYD6NUFINVJR3PQJ/events.json","paper":"https://pith.science/paper/KOB76DQG"},"agent_actions":{"view_html":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ","download_json":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ.json","view_paper":"https://pith.science/paper/KOB76DQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02540&json=true","fetch_graph":"https://pith.science/api/pith-number/KOB76DQGQWWYD6NUFINVJR3PQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KOB76DQGQWWYD6NUFINVJR3PQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ/action/storage_attestation","attest_author":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ/action/author_attestation","sign_citation":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ/action/citation_signature","submit_replication":"https://pith.science/pith/KOB76DQGQWWYD6NUFINVJR3PQJ/action/replication_record"}},"created_at":"2026-07-05T10:18:08.738097+00:00","updated_at":"2026-07-05T10:18:08.738097+00:00"}