SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention | Paper Citation Record

Observation 5a324224-5280-4233-94ea-e11a6f6e2c98 · outbound

This paper cites RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.637885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dd799a4-2f3c-4c39-a933-310f81b9fec4 · outbound

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

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.644170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b484e1c4-ea67-435e-a1eb-1cd2143fd3fe · outbound

This paper cites Sparse-vdit: Unleashing the power of sparse attention to accelerate video diffusion transformers.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Sparse-vdit: Unleashing the power of sparse attention to accelerate video diffusion transformers

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.521620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e79df23d-4e39-4241-aebc-c177e61b134c · outbound

This paper cites Re-ttention: Ultra sparse visual generation via attention statistical reshape.Proc.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Re-ttention: Ultra sparse visual generation via attention statistical reshape.Proc

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.504455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6cf9c132-c2ae-48e1-99e5-4f401702ee4c · outbound

This paper cites Quantsparse: Comprehensively compressing video diffusion transformer with model quantization and attention sparsification.arXiv preprint arXiv:2509.23681, 2025.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Quantsparse: Comprehensively compressing video diffusion transformer with model quantization and attention sparsification.arXiv preprint arXiv:2509.23681, 2025

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.659428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef2d5a8-d721-4f28-b4fa-9c75bb2e0e37 · outbound

This paper cites LVSA: Training-Free Sparse Attention for Long Video Diffusion.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention LVSA: Training-Free Sparse Attention for Long Video Diffusion

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:09.062372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 05c8b09d-8548-4439-8717-ddb0e72d007a · outbound

This paper cites Generalized neighborhood attention: Multi-dimensional sparse attention at the speed of light.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Generalized neighborhood attention: Multi-dimensional sparse attention at the speed of light

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.488074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8e6d715e-0b4f-4717-a6fb-b4724da7bb7e · outbound

This paper cites DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:09.039653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c457f2fb-715e-4b04-9cc9-a088576c285a · outbound

This paper cites Vbench: Comprehensive benchmark suite for video generative models.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Vbench: Comprehensive benchmark suite for video generative models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.680162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98590ed1-104c-48be-81b9-720ff17c7fba · outbound

This paper cites VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.684780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc974886-5f83-4db6-a70e-5438c5797e11 · outbound

This paper cites Product quantization for nearest neighbor search.IEEE transactions on pattern analysis and machine intelligence, 33(1):117–128, 2010.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Product quantization for nearest neighbor search.IEEE transactions on pattern analysis and machine intelligence, 33(1):117–128, 2010

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.689826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aae00f0-3826-4ad9-8785-e5bc40ea0aa6 · outbound

This paper cites Lookat: Lookup-optimized key-attention for memory-efficient transformers.arXiv preprint arXiv:2601.10155, 2026.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Lookat: Lookup-optimized key-attention for memory-efficient transformers.arXiv preprint arXiv:2601.10155, 2026

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.694430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1fe79f9-82a9-4c0f-a5b7-970b6a534cb6 · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.699084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a5def3-5c4f-4639-b2f6-92f92d852869 · outbound

This paper cites HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:08.919394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cd1aa6d1-ca4c-4c6b-ab41-a0d5a5d52467 · outbound

This paper cites Pisa: Piecewise sparse attention is wiser for efficient diffusion transformers.arXiv preprint arXiv:2602.01077, 2026.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Pisa: Piecewise sparse attention is wiser for efficient diffusion transformers.arXiv preprint arXiv:2602.01077, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.709836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb5a905e-fd21-40a0-a7cc-83e28f5dc58d · outbound

This paper cites Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.715376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 868df452-19e4-45c2-ade6-1cefdcffb616 · outbound

This paper cites Radial attention:O(nlogn )sparse attention with energy decay for long video generation.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Radial attention:O(nlogn )sparse attention with energy decay for long video generation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.450063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 78b67b81-e9ed-45d5-b1d4-1f82cdba41cd · outbound

This paper cites Astraea: A token-wise acceleration framework for video diffusion transformers.arXiv preprint arXiv:2506.05096, 2025.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Astraea: A token-wise acceleration framework for video diffusion transformers.arXiv preprint arXiv:2506.05096, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.725439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1464625-9322-483e-800b-38cbb8beea61 · outbound

This paper cites Rectified spaattn: Revisiting attention sparsity for efficient video generation.arXiv preprint arXiv:2511.19835, 2025.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Rectified spaattn: Revisiting attention sparsity for efficient video generation.arXiv preprint arXiv:2511.19835, 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.730698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3680c9f9-f598-42de-9b4b-f4a356211bc3 · outbound

This paper cites Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.735247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 107b978b-e8df-4b3e-8f07-e06a2a51683f · outbound

This paper cites RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:08.645838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f3dc8946-fc91-4a29-84b7-d7834bc26a13 · outbound

This paper cites DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:08.617826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0a5a4f92-1b25-4348-9211-18374f3b59eb · outbound

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

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.749953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97f893fb-5d59-41d2-8193-52a1aec357b5 · outbound

This paper cites Latte: Latent Diffusion Transformer for Video Generation.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Latte: Latent Diffusion Transformer for Video Generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.754608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88e5a942-f7a7-4438-a202-c58903dcdb0c · outbound

This paper cites Scalable diffusion models with transformers.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Scalable diffusion models with transformers

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.433650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cb4ed558-17e6-40ba-825d-668f6f885576 · outbound

This paper cites Flashomni: A unified sparse attention engine for diffusion transformers.arXiv preprint arXiv:2509.25401, 2025.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Flashomni: A unified sparse attention engine for diffusion transformers.arXiv preprint arXiv:2509.25401, 2025

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.763992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e5acc8b-c681-4a6e-85f2-429ec8ba351e · outbound

This paper cites Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.769382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72a11d85-c79c-4db8-9df3-262c0d805b44 · outbound

This paper cites DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.774458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 735b6f26-71cc-44d1-addc-809397494d38 · outbound

This paper cites Liteattention: A temporal sparse attention for diffusion transformers.arXiv preprint arXiv:2511.11062, 2025.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Liteattention: A temporal sparse attention for diffusion transformers.arXiv preprint arXiv:2511.11062, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.779722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e29b73f8-9c88-4619-b911-6236fab0c850 · outbound

This paper cites CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.784659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25695b32-c12d-49f5-b955-4ba2b9793e4e · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.790309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f69dfe3-3cec-41f7-8d7a-155e7a32593a · outbound

This paper cites Vorta: Efficient video diffusion via routing sparse attention.Proc.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Vorta: Efficient video diffusion via routing sparse attention.Proc

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.404758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 690e05f7-51a1-4d5d-ab53-140a5b71df30 · outbound

This paper cites Adacluster: Adaptive query-key clustering for sparse attention in video generation.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Adacluster: Adaptive query-key clustering for sparse attention in video generation

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.388147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f7b7e51f-912e-4d0e-a58c-58063fe27cf5 · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Wan: Open and Advanced Large-Scale Video Generative Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.806469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2376aa9-4b97-4d69-ab60-55c33077f7f2 · outbound

This paper cites Fasa: Frequency-aware sparse attention.arXiv preprint arXiv:2602.03152, 2026.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Fasa: Frequency-aware sparse attention.arXiv preprint arXiv:2602.03152, 2026

Reference 35

Resolution: verified exact; raw_fallback, observed 2026-08-15T23:30:08.354673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2ff9ab59-6e12-4c30-88ed-53ad1b5f5348 · outbound

This paper cites VideoRoPE: What Makes for Good Video Rotary Position Embedding?.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.816596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f27e8ee1-3c8c-4765-8c83-dafa5390b844 · outbound

This paper cites VMoBA: Mixture-of-Block Attention for Video Diffusion Models.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.821403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5df289fa-8e60-4e98-98d4-661907ba3089 · outbound

This paper cites Sparse video-gen: Accelerating video diffusion transformers with spatial-temporal sparsity.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Sparse video-gen: Accelerating video diffusion transformers with spatial-temporal sparsity

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.371750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 48642457-7f28-4c2b-91e4-142fa7a01d27 · outbound

This paper cites Training-free and adaptive sparse attention for efficient long video generation.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Training-free and adaptive sparse attention for efficient long video generation

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.355123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 423d7e9f-f99b-46ee-9969-7a43c23c451b · outbound

This paper cites Xattention: Block sparse attention with antidiagonal scoring.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Xattention: Block sparse attention with antidiagonal scoring

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.338357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 43e04f33-0ab5-4a1e-9a59-49ccb2b638cf · outbound

This paper cites Sparse videogen2: Accelerate video generation with sparse attention via semantic-aware permutation.Proc.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Sparse videogen2: Accelerate video generation with sparse attention via semantic-aware permutation.Proc

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.322939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fe117a85-54e7-4dff-bc25-d95863ef1039 · outbound

This paper cites Self-indexing kvcache: Predicting sparse attention from compressed keys.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Self-indexing kvcache: Predicting sparse attention from compressed keys

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.305669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4fd7bad1-c543-4b8d-af1d-40043b779c7c · outbound

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

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Cogvideox: Text-to-video diffusion models with an expert transformer

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.289386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 00fa192d-9574-4828-b535-dc5be76e2d21 · outbound

This paper cites Accelerating text-to-video generation with calibrated sparse attention.arXiv preprint arXiv:2603.05503, 2026.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Accelerating text-to-video generation with calibrated sparse attention.arXiv preprint arXiv:2603.05503, 2026

Reference 44

Resolution: verified exact; raw_fallback, observed 2026-08-15T23:30:08.230094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 17e6bcf9-62eb-4d09-9c33-726cf29548c8 · outbound

This paper cites Pqcache: Product quantization-based kvcache for long context llm inference.Proceedings of the ACM on Management of Data, 3(3):1–30, 2025.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Pqcache: Product quantization-based kvcache for long context llm inference.Proceedings of the ACM on Management of Data, 3(3):1–30, 2025

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.269370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8da8c947-efc0-44cb-a78d-81c4106e4813 · outbound

This paper cites Spargeattention: Accurate and training-free sparse attention accelerating any model inference.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Spargeattention: Accurate and training-free sparse attention accelerating any model inference

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.251234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 92502b9b-74c7-4810-8b1d-1d5f22a37990 · outbound

This paper cites Spargeattention2: Trainable sparse attention via hybrid top-k+ top-p masking and distillation fine-tuning.arXiv preprint arXiv:2602.13515, 2026.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Spargeattention2: Trainable sparse attention via hybrid top-k+ top-p masking and distillation fine-tuning.arXiv preprint arXiv:2602.13515, 2026

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.870032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec9be79b-e352-4bf6-8f90-44e5badb3883 · outbound

This paper cites Fast video generation with sliding tile attention.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Fast video generation with sliding tile attention

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.235151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aa837043-30e1-4913-8028-b884d7c67413 · outbound

This paper cites Faster video diffusion with trainable sparse attention.Proc.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Faster video diffusion with trainable sparse attention.Proc

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.218753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8b0084a6-f1b7-436e-855d-75b95adbef61 · outbound

This paper cites Nomad-attention: Efficient llm inference on cpus through multiply-add-free attention.Proc.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Nomad-attention: Efficient llm inference on cpus through multiply-add-free attention.Proc

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.201028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 096d854b-0517-4a37-9e28-fb6c51be1b55 · outbound

This paper cites Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T23:30:07.889075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fc9d90c-24c8-4aac-96d3-2520f226fa12 · outbound

This paper cites Paroattention: Pattern-aware reordering for efficient sparse and quantized attention in visual generation models.Proc.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Paroattention: Pattern-aware reordering for efficient sparse and quantized attention in visual generation models.Proc

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:30:09.185029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 14665521-f5d4-487b-88cd-67fd6d74b443 · outbound

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

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:08.038611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ee3f7132-d7ff-49b4-818e-11d14b6cb7ab · outbound

This paper cites ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:08.012986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5fe4a4fb-5b6a-41cc-84f4-1a53548fb550 · outbound

This paper cites SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:07.988353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4d1ebeb4-3692-404f-9a7a-f9cb5790f94d · outbound

This paper cites Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps.

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:30:07.964384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers