{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LHE4QCVDK6RAMT4DEPU7G5XIP5","short_pith_number":"pith:LHE4QCVD","schema_version":"1.0","canonical_sha256":"59c9c80aa357a2064f8323e9f376e87f773c399309be17adb5c7b0ed1f1b3ef6","source":{"kind":"arxiv","id":"2407.01425","version":1},"attestation_state":"computed","paper":{"title":"FORA: Fast-Forward Caching in Diffusion Transformer Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ilya Zharkov, Luming Liang, Pratheba Selvaraju, Tianyi Chen, Tianyu Ding","submitted_at":"2024-07-01T16:14:37Z","abstract_excerpt":"Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance. However, the increased size of these models leads to higher inference costs, making them less attractive for real-time applications. We present Fast-FORward CAching (FORA), a simple yet effective approach designed to accelerate DiT by exploiting the repetitive nature of the diffusion process. FORA implements a caching mechanism that stores and reuses intermediate outputs from the a"},"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":"2407.01425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T16:14:37Z","cross_cats_sorted":[],"title_canon_sha256":"e176121bf7b6a5a3acc8fc808be7666fdc0d474f9ecbc09be216ba1cc474813b","abstract_canon_sha256":"c28d1a4124a1d1072bbf28e320b0d383add3ea37410da5f28f503f927851e199"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:47.791831Z","signature_b64":"tjm73KoozOmmRcBDnZ7N6ASGz7b7ROgoMBCSdICuOvnWl2ZD4I1cG8gT0uy7o5TpuOnnnBbMxYcwGJZe9WFHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59c9c80aa357a2064f8323e9f376e87f773c399309be17adb5c7b0ed1f1b3ef6","last_reissued_at":"2026-07-05T08:38:47.791408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:47.791408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FORA: Fast-Forward Caching in Diffusion Transformer Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ilya Zharkov, Luming Liang, Pratheba Selvaraju, Tianyi Chen, Tianyu Ding","submitted_at":"2024-07-01T16:14:37Z","abstract_excerpt":"Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance. However, the increased size of these models leads to higher inference costs, making them less attractive for real-time applications. We present Fast-FORward CAching (FORA), a simple yet effective approach designed to accelerate DiT by exploiting the repetitive nature of the diffusion process. FORA implements a caching mechanism that stores and reuses intermediate outputs from the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01425","kind":"arxiv","version":1},"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/2407.01425/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":"2407.01425","created_at":"2026-07-05T08:38:47.791470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01425v1","created_at":"2026-07-05T08:38:47.791470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01425","created_at":"2026-07-05T08:38:47.791470+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHE4QCVDK6RA","created_at":"2026-07-05T08:38:47.791470+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHE4QCVDK6RAMT4D","created_at":"2026-07-05T08:38:47.791470+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHE4QCVD","created_at":"2026-07-05T08:38:47.791470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26769","citing_title":"ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26778","citing_title":"LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26795","citing_title":"NaviCache: Test-Time Self-Calibration Caching for Video Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06060","citing_title":"ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30849","citing_title":"SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29360","citing_title":"SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26632","citing_title":"RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25798","citing_title":"DiSC: Resolution-Scalable Acceleration of Diffusion Models by Exploiting Sparsity and Cached Token Reuse with Hash-based Distribution","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27075","citing_title":"BeCARE: Budgeted Cache Refresh for Diffusion Transformer Acceleration","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23381","citing_title":"VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22015","citing_title":"ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12894","citing_title":"Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18346","citing_title":"Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13456","citing_title":"Block-wise Adaptive Caching for Accelerating Diffusion Policy","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05449","citing_title":"DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13357","citing_title":"AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01725","citing_title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13316","citing_title":"Test-time Sparsity for Extreme Fast Action Diffusion","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04018","citing_title":"1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11869","citing_title":"FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09003","citing_title":"FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09003","citing_title":"FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02152","citing_title":"SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01725","citing_title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5","json":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5.json","graph_json":"https://pith.science/api/pith-number/LHE4QCVDK6RAMT4DEPU7G5XIP5/graph.json","events_json":"https://pith.science/api/pith-number/LHE4QCVDK6RAMT4DEPU7G5XIP5/events.json","paper":"https://pith.science/paper/LHE4QCVD"},"agent_actions":{"view_html":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5","download_json":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5.json","view_paper":"https://pith.science/paper/LHE4QCVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01425&json=true","fetch_graph":"https://pith.science/api/pith-number/LHE4QCVDK6RAMT4DEPU7G5XIP5/graph.json","fetch_events":"https://pith.science/api/pith-number/LHE4QCVDK6RAMT4DEPU7G5XIP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5/action/storage_attestation","attest_author":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5/action/author_attestation","sign_citation":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5/action/citation_signature","submit_replication":"https://pith.science/pith/LHE4QCVDK6RAMT4DEPU7G5XIP5/action/replication_record"}},"created_at":"2026-07-05T08:38:47.791470+00:00","updated_at":"2026-07-05T08:38:47.791470+00:00"}