Paper Citation Record · LEDGER

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy

As of 14 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 4 inbound Pith citation observations for arXiv:2505.21036.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.21036 v2

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:45:11.721662Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:51:04.877354Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-16T19:18:19.379629Z

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy20
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8e826e5d-1fb4-4f55-9976-49de5a5ebfcb · outbound

This paper cites Stable video diffusion: Scaling latent video diffusion models to large datasets, 2023.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Stable video diffusion: Scaling latent video diffusion models to large datasets, 2023

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:07.482788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ab7e092-0de3-4f98-a2b9-1c61bc9da826 · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:07.580972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb34eed6-21ba-42bc-9a8e-d269833307e2 · outbound

This paper cites Token merging for fast sta- ble diffusion.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Token merging for fast sta- ble diffusion

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:07.676013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31379dd5-0ac8-42ab-9be8-62a77e30396c · outbound

This paper cites Pixart-σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Pixart-σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:17.417453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a21aa5d3-7985-4854-a5f7-c033b13ee342 · outbound

This paper cites $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:07.888936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd28979-e471-4634-acd9-78171c899646 · outbound

This paper cites an unresolved cited work.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:45:16.323152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1fca4931-29d7-4fc7-b4ea-18a2cb4f4a27 · outbound

This paper cites Sparsevit: Revisiting activation spar- sity for efficient high-resolution vision transformer.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Sparsevit: Revisiting activation spar- sity for efficient high-resolution vision transformer

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:15.979685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation eaebfb49-9fbd-43fc-b10c-7d53a28dd30f · outbound

This paper cites Guided diffusion models.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Guided diffusion models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:15.733230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 531903ff-bc9a-430d-a6a3-138e0a67ab41 · outbound

This paper cites Streamingt2v: Con- sistent, dynamic, and extendable long video generation from text, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Streamingt2v: Con- sistent, dynamic, and extendable long video generation from text, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:15.530425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3e75432e-d60a-47fa-b596-33d4ca3a24a6 · outbound

This paper cites Denoising dif- fusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Denoising dif- fusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:08.489795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7cd8a0-70c2-4ad6-946d-55eeea6ea71b · outbound

This paper cites Vbench: Com- prehensive benchmark suite for video generative models,.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Vbench: Com- prehensive benchmark suite for video generative models,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:08.580591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bd41059-7b7f-4169-b019-e16a48cc4801 · outbound

This paper cites Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:15.288103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3867898e-c4a8-4056-af74-aeb2232f9bf4 · outbound

This paper cites Ryoo, and Tian Xie.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Ryoo, and Tian Xie

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:15.112273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9bb9b5b1-e570-4715-8f55-616f122452be · outbound

This paper cites Hunyuanvideo: A systematic framework for large video generative models, 2025.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Hunyuanvideo: A systematic framework for large video generative models, 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:14.890322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c9a18f24-7db6-457c-b701-5511eda5e1bf · outbound

This paper cites Autodiffusion: Training-free optimization of time steps and architectures for automated diffusion model accelera- tion, 2023.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Autodiffusion: Training-free optimization of time steps and architectures for automated diffusion model accelera- tion, 2023

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:14.637404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d61add74-36d4-4f4b-b6cd-d09746a70779 · outbound

This paper cites Timestep embedding tells: It’s time to cache for video diffusion model, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Timestep embedding tells: It’s time to cache for video diffusion model, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:14.488801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 473762dc-7121-4785-8e69-98763ba75f80 · outbound

This paper cites Faster diffu- sion via temporal attention decomposition.arXiv e-prints, pages arXiv–2404, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Faster diffu- sion via temporal attention decomposition.arXiv e-prints, pages arXiv–2404, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:14.261625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 217115a7-43d7-4c3a-b3e9-819c3e50a512 · outbound

This paper cites Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:09.302188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c3a417-8360-489f-b328-292dce66eb14 · outbound

This paper cites Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:09.410733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd4a77e-0654-429e-89a1-adfba321a082 · outbound

This paper cites Deepcache: Accelerating diffusion models for free.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Deepcache: Accelerating diffusion models for free

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:14.042995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d90b3ad9-ee1e-4ef7-b1d2-92de1ae52aad · outbound

This paper cites Latte: La- tent diffusion transformer for video generation, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Latte: La- tent diffusion transformer for video generation, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:13.867592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cd872d48-93b3-48b0-a87c-73d41cc94c2d · outbound

This paper cites Improved denoising diffusion probabilistic models.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Improved denoising diffusion probabilistic models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:09.701322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93fb295f-38d1-41be-b56b-cc29136bc3da · outbound

This paper cites Sora prompt, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Sora prompt, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:13.676567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e024d2e6-6b3e-43eb-9ed2-5553a5d8a455 · outbound

This paper cites an unresolved cited work.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:45:13.444749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 04c17016-bc8a-4555-875d-8be49d168dd8 · outbound

This paper cites Scalable diffusion models with transformers.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Scalable diffusion models with transformers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:09.975017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb34d52-44c6-4cc3-8d1a-a93415680d73 · outbound

This paper cites Open-sora plan, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Open-sora plan, 2024

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:13.208777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8eba9ccf-3671-4694-8624-8e8757109417 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:10.141616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11372372-ede3-44a7-b03f-493bcfa97701 · outbound

This paper cites Sampson, Shikai Li, Simone Parmeggiani, Steve Fine, Tara Fowler, Vladan Petro- vic, and Yuming Du.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Sampson, Shikai Li, Simone Parmeggiani, Steve Fine, Tara Fowler, Vladan Petro- vic, and Yuming Du

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:13.044913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 41116385-9e10-4d9c-b4e9-e4737b966c68 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy High-resolution image synthesis with latent diffusion models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:10.284805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3ee62d5-62c7-46c1-aad7-95798887685e · outbound

This paper cites Align your steps: Optimizing sampling schedules in diffusion mod- els, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Align your steps: Optimizing sampling schedules in diffusion mod- els, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:12.887592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5228e9aa-bed7-478a-a789-29b66c54ffbb · outbound

This paper cites ToDo: Token Downsampling for Efficient Generation of High-Resolution Images.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy ToDo: Token Downsampling for Efficient Generation of High-Resolution Images

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:10.504069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb6e90a9-0ba2-4a1f-b48c-2bbf0d71dc5c · outbound

This paper cites RazorAttention: Efficient KV Cache Compression Through Retrieval Heads.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy RazorAttention: Efficient KV Cache Compression Through Retrieval Heads

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:10.611325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bae6101f-c381-4ef6-be11-eb1c67b6e2fc · outbound

This paper cites U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:10.697695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fc248c8-b9e8-470d-9008-c68df22fef9c · outbound

This paper cites Accelerating trans- formers with spectrum-preserving token merging.Advances in Neural Information Processing Systems, 37:30772–30810,.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Accelerating trans- formers with spectrum-preserving token merging.Advances in Neural Information Processing Systems, 37:30772–30810,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:10.828811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4207060-fe0f-42a6-9a4c-34ac75fd5351 · outbound

This paper cites Attention-driven training-free efficiency enhancement of diffusion models.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Attention-driven training-free efficiency enhancement of diffusion models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:12.640493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d21b4e0a-d722-4819-ae60-8211139ffdbd · outbound

This paper cites Cache me if you can: Accel- erating diffusion models through block caching.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Cache me if you can: Accel- erating diffusion models through block caching

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:12.444608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 11c4e6df-aab0-4c74-b5df-e9e305935ad8 · outbound

This paper cites Importance-Based Token Merging for Efficient Image and Video Generation.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Importance-Based Token Merging for Efficient Image and Video Generation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:11.197151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28a836d7-a604-44bd-b446-d255f7676526 · outbound

This paper cites Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:11.296944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c2a597b-b140-47a7-bb0c-05712ed7e110 · outbound

This paper cites Cogvideox: Text-to-video diffusion models with an expert transformer, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Cogvideox: Text-to-video diffusion models with an expert transformer, 2024

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:12.207778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1d80df88-db1c-4fba-ae80-e5d34a590f87 · outbound

This paper cites Ditfastattn: Attention compression for diffusion transformer models, 2024.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Ditfastattn: Attention compression for diffusion transformer models, 2024

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:12.005328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5f47e94f-c121-4f8e-bca6-2792189ad26b · outbound

This paper cites OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:11.664328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00149e4-fb4f-4ec2-8388-fd24fdd72370 · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Open-Sora: Democratizing Efficient Video Production for All

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:11.721662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bf589556-c1e2-4d91-8b0d-f413ca89f1fc · inbound

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models cites this paper.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:51:04.877354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a686bba-b8af-4dd5-a5ef-bc2827d95f69 · inbound

RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention cites this paper.

RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-16T19:18:19.381537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4d2ac67c-cca4-4fe7-b430-e8991765f54b · inbound

Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering cites this paper.

Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-15T08:59:53.225273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d75c50f4-ebb0-4ac4-a96a-4f25e1ea86b1 · inbound

HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion cites this paper.

HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:19:46.033033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.