Pith. sign in

Paper Citation Record · LEDGER

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

As of 19 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 3 inbound Pith citation observations for arXiv:2506.16054.

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

pith.paper-citation-record.v1
2506.16054 v1

Coverage vector

measured 70 of 70 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:51:05.625977Z

measured 73 of 73 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T09:22:55.731241Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T09:49:44.827683Z

Reference resolution

70 of 70 outbound references displayed

  • verified exact0
  • verified fuzzy37
  • unresolved33
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 40f13473-88e0-492b-8552-0051ecffe199 · outbound

This paper cites https://resources.nvidia.com/en-us-tensor-core ,.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models https://resources.nvidia.com/en-us-tensor-core ,

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.245372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:04.489965Z digest=sha256:de9556ac0244fd8f662271e9352f4e847181912926860f86b415371a9c485ae4

Observation 22107bba-3e60-458f-8b00-34068849c014 · outbound

This paper cites https://docs.amd.com/r/2021.2-English/ug1483-model-composer-sys-gen-user-guide/ DSP48E,.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models https://docs.amd.com/r/2021.2-English/ug1483-model-composer-sys-gen-user-guide/ DSP48E,

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.228724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:04.595686Z digest=sha256:b4037437502b8711266e7e7dfdb73ddae8df91428ae51979485ffda21ecb50f1

Observation be31a550-e543-4b19-a6c7-9dca606affdf · outbound

This paper cites Moba: Mixture of block attention.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Moba: Mixture of block attention

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.211648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:04.682196Z digest=sha256:e2b564a45d688d0a9e5fdf603b3904a5a1d7c063b63fa1e738417065ba178457

Observation ac339383-4460-4ea8-8591-a194a701b9e7 · outbound

This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:04.792773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:04.792773Z digest=sha256:be879be8ba976e0da74ea3433d428700394cd11f57ed412dbeb01b5f1fa5dc3e

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

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

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.

source=pdf_text observed=2026-08-06T23:51:04.877354Z digest=sha256:7054654d2506f54ca1f6b8f5f163fb8fcf501672a9ad724ca8d2c368d9b67e17

Observation 81a09fc4-af98-4d86-a281-ec2dce407603 · outbound

This paper cites Pixart- α: Fast training of diffusion transformer for photorealistic text-to-image synthesis, 2023.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Pixart- α: Fast training of diffusion transformer for photorealistic text-to-image synthesis, 2023

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.195285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.017856Z digest=sha256:34ac196fa15cd8ba04c7fca317f23b79f76596b898a32d58bc74038a37abb3e9

Observation 65439646-eafa-4f93-8680-4b93e0e56dcf · outbound

This paper cites Hardware acceleration of sparse and irregular tensor computations of ml models: A survey and insights.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Hardware acceleration of sparse and irregular tensor computations of ml models: A survey and insights

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.179828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.053929Z digest=sha256:bd957fc52ac3975bd729e04509e4c2d7200cd09a332f71399b1f55b7a5d3b93b

Observation 9862f58b-5461-4252-ae6a-b5497ede07ed · outbound

This paper cites Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.186517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.186517Z digest=sha256:e7da175e002f327ea19e7a11c4e2b595db8f5a257b19326e5f1546d3da491774

Observation 8e6ea537-b7fc-4a28-acc5-ad995ed85e24 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.296552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.296552Z digest=sha256:7e589bd9ee45e2f58232de60fc1ffe4fe74bf6756495e0a01552c0ba2cf645c4

Observation 35edc0f1-42d0-4bba-88db-b80ba96dc7b4 · outbound

This paper cites R2r: Efficiently navigating divergent reasoning paths with small-large model token routing.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models R2r: Efficiently navigating divergent reasoning paths with small-large model token routing

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.307908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.307908Z digest=sha256:c1c38c363ec511ff977457bf0c5d3bb2b748deb161dfe3b0a1461c1afc37dedc

Observation ff253678-ee5e-475b-9449-27e353da9db6 · outbound

This paper cites Moa: Mixture of sparse attention for automatic large language model compression, 2024.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Moa: Mixture of sparse attention for automatic large language model compression, 2024

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.163791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.312568Z digest=sha256:810ad5a4805bba343815c332c7f7cddb6851d44d683f8740e26ba79a48d41205

Observation ca7d1ebe-c8c2-49ed-9433-75b741fd4dc1 · outbound

This paper cites FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.316975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.316975Z digest=sha256:0087669c2a3ca2a783c6c1b59d5d53fc1db62d4f9be04f1836dc8a63cc879194

Observation 1c53dc3a-6247-42a8-bf01-82c913187c3f · outbound

This paper cites Clipscore: A reference-free evaluation metric for image captioning.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Clipscore: A reference-free evaluation metric for image captioning

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.147052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.322466Z digest=sha256:a780e5d7fd66a92524544a1e2ba30830cf0fd062bebf125887d3c3239521c9b9

Observation 70c0bf38-4b18-49e2-b9ee-402b1413667b · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Gans trained by a two time-scale update rule converge to a local nash equilibrium

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.131021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.327560Z digest=sha256:987782bdef29ed879f46939e24a4275c1d92b13f75008932afdc7a1edb76a48a

Observation 197f0536-f34e-4010-b0c7-9506d72aa179 · outbound

This paper cites Open-Sora.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Open-Sora

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.114317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.331841Z digest=sha256:cee6afdd33ce2be1c80fe2443f08d76c5108ea051ed1f1fb2d32be807be4cb19

Observation 6065c072-55c3-458e-b9f3-fb4b310eef5b · outbound

This paper cites Qvgen: Pushing the limit of quantized video generative models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Qvgen: Pushing the limit of quantized video generative models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.336621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.336621Z digest=sha256:c5846881608c6542d01d95810434a79526799568da65798aa7c1eb6d20060632

Observation f320bd9e-5f10-4597-96fe-2cd2ae9cb08e · outbound

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

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models VBench: Comprehensive Benchmark Suite for Video Generative Models

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.341299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.341299Z digest=sha256:1c4526a5525281300b8e8d6471405c536501978004740684c1d0a94659d4d1ef

Observation 74f81c97-9fdd-443a-ac6a-295c489b7551 · outbound

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

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.097510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.346754Z digest=sha256:46fb719fae07ed2e479feadb29933839dbe7074533a606969604f4c7af7b520e

Observation e0d75ec8-a19c-4fd9-af8a-34f25fd55248 · outbound

This paper cites Flux.1: A high-quality text-to-image model.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Flux.1: A high-quality text-to-image model

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.080670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.351284Z digest=sha256:88c5f40578dc3b417cbb362a8a45c18b26d17939bc154f34b8a514af961824ed

Observation d85b7bbf-d45f-4ca2-90db-e93fe302d280 · outbound

This paper cites Flexprefill: A context-aware sparse attention mechanism for efficient long-sequence inference, 2025.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Flexprefill: A context-aware sparse attention mechanism for efficient long-sequence inference, 2025

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.064891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.355637Z digest=sha256:fb35993fe887cc51df5f10365b2909ed9fe9eb6c8fb45be69fcd16c729be53ea

Observation e10f7041-f47d-4b42-b356-5e4dd725026e · outbound

This paper cites Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.359947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.359947Z digest=sha256:8c78e04c0be300b66d01890dc380c3df0740aa20ba4997cbc625ed329cc66d89

Observation d8411e65-4afe-4107-9b81-5b0f96ab574d · outbound

This paper cites Mbq: Modality-balanced quantization for large vision-language models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Mbq: Modality-balanced quantization for large vision-language models

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.048138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.364491Z digest=sha256:792203bb881f52d5ead43da743754d2fe8f516ad97ba69438741561a5b379abd

Observation cd399d00-fa43-4ec2-ac3c-053644d1f619 · outbound

This paper cites Evaluating quantized large language models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Evaluating quantized large language models

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.029985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.368760Z digest=sha256:faffa6113bcbb593e9cd3c9f78b2caeaf9339d67160eeddff1a062206d2c2eb2

Observation c9fbb866-6e7e-4ac0-8923-1eec75bee05f · outbound

This paper cites Q-diffusion: Quantizing diffusion models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Q-diffusion: Quantizing diffusion models

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:07.013456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.373045Z digest=sha256:ea57d981eefcd75fc5f488abbe8b2340c01bda4ac2371df5a4234e28fc4b3648

Observation f3e3e0be-b8e7-4a3a-a3bd-34492836fef8 · outbound

This paper cites TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.377160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.377160Z digest=sha256:8209c083c94aefa0734d58e49bdc09f41a26a8f2f47bd4641688d2765460fb3f

Observation 97fd9b32-a573-4da2-9428-7d2c82926f23 · outbound

This paper cites Duquant: Distributing outliers via dual transformation makes stronger quantized llms.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Duquant: Distributing outliers via dual transformation makes stronger quantized llms

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.996393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.382277Z digest=sha256:ec1c27c25c79b6197bfb5c41df2e97407881ab67eabc30a83f71376b6339cea7

Observation c16a4583-0fd7-4fb4-9790-2f02c162bd6d · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.387096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.387096Z digest=sha256:e09682eb547f09abdd9d59b779ba357f7ae91eb32ebc2ef564cc3ccb6a75051d

Observation 83de083e-ed3f-4d35-a19f-aa8be04c7895 · outbound

This paper cites Lawrence Zitnick, and Piotr Dollár.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Lawrence Zitnick, and Piotr Dollár

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.980247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.391787Z digest=sha256:3ccdc45ff99b9144778f2d25c8fd5c74d1dfb557c34c99c8b02dfe703773cd4e

Observation 0c7bfd5d-7842-4cd9-8446-a2f147022ddb · outbound

This paper cites FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.396844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.396844Z digest=sha256:fad1b5bd874fe01f1ba209f6eb33a5f9d70a6f0f54cda26b7c413bdc1c7f48f1

Observation 8f1e34e4-af45-4e1e-a329-a8bf8030d791 · outbound

This paper cites From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.401910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.401910Z digest=sha256:d2e98c93cf8435069defa96550bd24d3c8e370faae1327ec3085572c51247a98

Observation df4693bc-bdfd-4a6e-9a8a-910229384ab7 · outbound

This paper cites PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.406333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.406333Z digest=sha256:c50bd9e59b0a3a3aa03743efc1478c107b404eeef5a2be0e31f6c92fdd752116

Observation a626de08-5c20-40af-b665-ff05536d79cd · outbound

This paper cites EvalCrafter: Benchmarking and Evaluating Large Video Generation Models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.411761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.411761Z digest=sha256:cee4da782151b42b69e4f7932abb01e57a675dc309bbfe69ee95b0e5741945cf

Observation 2726c9ee-4f9c-4433-9cb6-3123e886caca · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Swin transformer: Hierarchical vision transformer using shifted windows

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.964518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.417257Z digest=sha256:833269eee81dd3ee4853ef55310d1b0ade91e993488874ef699bd743a99ccfa7

Observation 9718ddbe-77f1-4a6b-a1a1-f470422cf245 · outbound

This paper cites A White Paper on Neural Network Quantization.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models A White Paper on Neural Network Quantization

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.422860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.422860Z digest=sha256:39aac4e476a7e812ba7785277eac2a9b0bcc7869ee5b7d2ef4a14a00d734f8a6

Observation fcc726ad-e46c-4467-9e50-78d7eddffe88 · outbound

This paper cites Scalable diffusion models with transformers, 2023.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Scalable diffusion models with transformers, 2023

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.948857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.428034Z digest=sha256:0b32efd8a681b14593740c7eb2909803a6ea4649f61c71c9a6654d5ec4005151

Observation 5fb43c8e-3ffa-4a87-888f-fcaed390b982 · outbound

This paper cites Post-training quantization on diffusion models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Post-training quantization on diffusion models

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.932492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.433628Z digest=sha256:4b6f01e8dd326065bee71e27da699b901888a1141bade01875e25e35d0e7f83c

Observation 1abf0676-b877-419c-b657-b294733098e2 · outbound

This paper cites Plug-and-play 1.x-bit kv cache quantization for video large language models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Plug-and-play 1.x-bit kv cache quantization for video large language models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.438352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.438352Z digest=sha256:db1abcf90b43d6d3f682e64a9821d426be07003eee6e33001d03d8de18a8a35c

Observation e6335c5e-33c0-4c9e-ba5a-8e43da91cdbe · outbound

This paper cites Cogvideox-5b.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Cogvideox-5b

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.916858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.443100Z digest=sha256:df1c9ce6aeb1d35497024df79f986d88ad68333bb61a55e4ed69816c3cf4acd6

Observation 808c4c4b-90b4-474a-92b2-8006f8100529 · outbound

This paper cites Fvd: A new metric for video generation.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Fvd: A new metric for video generation

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.899504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.448387Z digest=sha256:fa1c03e21896ba6e10e4ba2c47b0cd2b85b9be2974f040de81be94a64b8427f5

Observation 797fc8e3-7acc-4280-a230-e06fbc66ead9 · outbound

This paper cites Attention is all you need.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Attention is all you need

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.882181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.453549Z digest=sha256:fa3a535eca15254ad30716b171745a467d2de3b47db3747d8939fc58b0aedf6f

Observation d09bb5e1-0b16-4106-b61c-d2c1abc95514 · outbound

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

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Wan: Open and Advanced Large-Scale Video Generative Models

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.459083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.459083Z digest=sha256:a39ea705369c8cbcf00813e0d0e0f34a8506f7d53638202c5602263c819db01b

Observation ba9e7812-4aeb-47e3-969c-81bb70d6c717 · outbound

This paper cites Image quality assessment: From error visibility to structural similarity.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Image quality assessment: From error visibility to structural similarity

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.866356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.465393Z digest=sha256:b59e21edf58944dea251a16f96f9857ca37509ab6c5c63d2eae336983bb46df4

Observation 2af81003-62fb-4016-98e5-7c1841e560db · outbound

This paper cites GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.470756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.470756Z digest=sha256:d9a587d6b97673a8e5949bceeeb85a315f1e5217b00b11812ef74a7174fe1674

Observation 29025d51-14d7-49c4-a750-8bbf77ac3595 · outbound

This paper cites Exploring video quality assessment on user generated contents from aesthetic and technical perspectives.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Exploring video quality assessment on user generated contents from aesthetic and technical perspectives

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.850114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.476900Z digest=sha256:bfc4b66472734245a9d360042d824a6ae6670f47bfbca2a2163597c9d29cb088

Observation 09f3f71e-2c8f-4692-ab8c-41ecd814d9a4 · outbound

This paper cites Sparse videogen: Accelerating video diffusion transformers with spatial-temporal sparsity, 2025.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Sparse videogen: Accelerating video diffusion transformers with spatial-temporal sparsity, 2025

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.831953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.483035Z digest=sha256:781b17c8f32b0fe2b176c61a504be59b6cf4051bb95872b7a7c31e9516704f35

Observation eb3176f0-b26e-4050-811a-2033d5ee0502 · outbound

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

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.488394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.488394Z digest=sha256:2178dc82760943919384f160eaa28a3ebd66407f4c807701f73900b966b50b4d

Observation edb0e63f-bca9-4cf9-a086-445fad910dfb · outbound

This paper cites Efficient multi-task llm quantization and serving for multiple lora adapters.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Efficient multi-task llm quantization and serving for multiple lora adapters

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.815417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.493901Z digest=sha256:d39aa901dbaf6ae018de4f52824c9cd9e93330d56db5b778913b0051eb2076ad

Observation 19a7852d-479e-450c-9889-535fd0a746c6 · outbound

This paper cites Training-free and adaptive sparse attention for efficient long video generation, 2025.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Training-free and adaptive sparse attention for efficient long video generation, 2025

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.500128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.500128Z digest=sha256:7ac8e1d4b38603fcc841427e82d4947b95436e5119d03e93da73088b8f83979e

Observation f3d561b9-8361-4088-926b-c1aa386268e3 · outbound

This paper cites Infllm: Training-free long-context extrapolation for llms with an efficient context memory,.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Infllm: Training-free long-context extrapolation for llms with an efficient context memory,

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.505477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.505477Z digest=sha256:a0ea371ad985ad7bf537d666128794d5306a767178884097860a6cf20d051907

Observation 987a1a00-881e-42f3-a533-a9ddfce3622f · outbound

This paper cites DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.511335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.511335Z digest=sha256:ee6ce9449926e0f7eb1d242d710364117a6f3b8229baff4647caed45d859b57b

Observation f8155a58-580c-469e-b3ec-98da7a163cb0 · outbound

This paper cites Efficient streaming language models with attention sinks, 2024.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Efficient streaming language models with attention sinks, 2024

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.778691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.517451Z digest=sha256:1ca951d5572781c06873e79c0514962c3ded97085b0ce8cd58c5847fa2e5fa3e

Observation fe5c8862-117c-40f9-a117-ba5ddff78986 · outbound

This paper cites EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.522354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.522354Z digest=sha256:10af8fe2f66ca05a61ff565375ba9034bad2cc1a2569e895f3d54963b2de712a

Observation 6810644c-df25-4459-ba20-0086de6a5fd9 · outbound

This paper cites Imagereward: Learning and evaluating human preferences for text-to-image generation, 2023.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Imagereward: Learning and evaluating human preferences for text-to-image generation, 2023

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.762134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.527741Z digest=sha256:aeec3518072e12e6c00f3b43449aa56e899d04d6ffe3e4b1eb5be6e0154b121e

Observation e89ccf27-81f0-47fa-897b-42b273e38716 · outbound

This paper cites Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.533597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.533597Z digest=sha256:6b7d6cb3abdc6b68e4e1f940d99ccf2ac37def087caee9c63babda1ef3462ab6

Observation 2a90d210-1879-4f2c-afd9-77c390433939 · outbound

This paper cites SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.539269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.539269Z digest=sha256:e975fc86cc89f4334cb9c265cd71f38e559005903f54805f0e6ec8ee45ce1b44

Observation 85e7ca4c-4869-4314-98fc-344ac48e69ca · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.544820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.544820Z digest=sha256:0f3e00110c64843b43e7ecf70b31ee3b12c26f81dde12f874602a7c9007455aa

Observation bd4237d9-5bba-4b84-a7cf-ff57294490ee · outbound

This paper cites DiTFastattn: Attention compression for diffusion transformer models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models DiTFastattn: Attention compression for diffusion transformer models

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.745330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.550531Z digest=sha256:e093da6381cf8adf24698a689c2d45b9c46db17326ff177f4e79ee03f656c116

Observation 28ea73ba-e42d-477b-946b-9fa96788e2d1 · outbound

This paper cites Big Bird: Transformers for Longer Sequences.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Big Bird: Transformers for Longer Sequences

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.556548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.556548Z digest=sha256:e9f7c42211efd34c9ccc70f07b8829f10f3bcb0c8b671d6d7d615ae400e1c193

Observation a9c8e80f-e931-49cb-8794-66e87f536836 · outbound

This paper cites Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization, 2024.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization, 2024

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.728865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.561782Z digest=sha256:b8e98b50661e1ebb0cf8b13af7bf90556f20aff8c80565af75d9c86743e3b026

Observation 1cfd8fa2-48a5-49cf-8675-dcebbfd6e4d8 · outbound

This paper cites Sageattention3: Microscaling fp4 attention for inference and an exploration of 8-bit training.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Sageattention3: Microscaling fp4 attention for inference and an exploration of 8-bit training

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.567177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.567177Z digest=sha256:d8279975f83eeb66551f73bf3f16b22b181d60b674062dd5e7d7dfc86c30e7de

Observation 772340de-aba6-4585-a1ad-545d2404a0b1 · outbound

This paper cites Sageattention: Accurate 8-bit attention for plug-and-play inference acceleration.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Sageattention: Accurate 8-bit attention for plug-and-play inference acceleration

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.711021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.572050Z digest=sha256:517320e57ef7be341914a3923a764c03f74689192124b87bdde7652f8c7a2124

Observation 60dd34f0-429e-45f0-aca4-0ccce2511578 · outbound

This paper cites Spargeattn: Accurate sparse attention accelerating any model inference.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Spargeattn: Accurate sparse attention accelerating any model inference

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.577632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.577632Z digest=sha256:36906dd68f897464280019376d0c67876438880e5c9f7612838f4e51cc86bc17

Observation 73e653c1-61fc-4678-b41a-9fb4739bcccf · outbound

This paper cites Spargeattn: Accurate sparse attention accelerating any model inference, 2025.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Spargeattn: Accurate sparse attention accelerating any model inference, 2025

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.692804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.583348Z digest=sha256:f3cf2920ba410da73542d349504ff9aa69bbc313dd2cb353c757a33cafc1853c

Observation bf026bb8-1c7a-4a69-91ea-331b455d0370 · outbound

This paper cites Fast Video Generation with Sliding Tile Attention.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Fast Video Generation with Sliding Tile Attention

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.591383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.591383Z digest=sha256:d30731a4a169c49ca426016e60fe278be868ec2e75f6cdf49a3d0e441c213e36

Observation aab87744-35e6-4f3a-93dd-d848650de30b · outbound

This paper cites Faster video diffusion with trainable sparse attention.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Faster video diffusion with trainable sparse attention

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.597518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.597518Z digest=sha256:035e0d0ef6abfee8830072a8d45b1ce743d1271e4df0d9278276c562d9ee1a5b

Observation 4dba0caa-bad5-4e6c-a16a-752d4abd5ae4 · outbound

This paper cites Accurate INT8 Training Through Dynamic Block-Level Fallback.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Accurate INT8 Training Through Dynamic Block-Level Fallback

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-06T23:51:05.603947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:51:05.603947Z digest=sha256:c160df1ac73bbd84e5cc382de7fbb3cf7a9954f2acb06ebcd948e869be0a7c00

Observation e12275ef-9160-4cc3-98c6-b137af8d12c5 · outbound

This paper cites H 2o: Heavy-hitter oracle for efficient generative inference of large language models, 2023.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models H 2o: Heavy-hitter oracle for efficient generative inference of large language models, 2023

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.676321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.609964Z digest=sha256:f942c52914729a9be8eff6bf4d6ed24c5336a7e724f44b2212d6c9a2ff3315de

Observation f4bf25be-015c-4fb9-8fb7-bf10ef0c9d89 · outbound

This paper cites Flasheval: Towards fast and accurate evaluation of text-to-image diffusion generative models.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Flasheval: Towards fast and accurate evaluation of text-to-image diffusion generative models

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.659813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.615547Z digest=sha256:0d1b8c7fa8b25065047a0e637a35fb54e7768a64469af3b29905be99eec76402

Observation e062e1eb-31cd-48cf-a5f8-934d6f50ca8c · outbound

This paper cites Vidit-q: Efficient and accurate quantization of diffusion transformers for image and video generation, 2025.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Vidit-q: Efficient and accurate quantization of diffusion transformers for image and video generation, 2025

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.642445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.620696Z digest=sha256:2af278c5e9f87f123e84b305be38c533206e4971e30d158b122ca1667c2c4c6b

Observation c4419178-731a-45bf-a357-94885e91fdc7 · outbound

This paper cites skipping.

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models skipping

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:51:06.624107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:51:05.625977Z digest=sha256:01a90c072a00361a240a88dc385db49a2b627df8b3f038c1b1bbd2ae3b016d0a

Pith citing papers

Observation dac1cfcd-a98a-4114-982a-36d5e4c07256 · inbound

Efficient Video Diffusion Models: Advancements and Challenges cites this paper.

Efficient Video Diffusion Models: Advancements and Challenges PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Reference 194

Resolution
verified exact
arxiv_id, observed 2026-05-10T09:03:26.339861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-10T08:28:29.706249Z digest=sha256:948ae4b6b968c310484abf89402fee4602932d0bb08163f02bfb06862f0469ed

Observation 908e6438-6909-4813-a979-f17ceb788497 · inbound

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

HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Reference 53

Resolution
verified exact
arxiv_id, observed 2026-05-15T05:19:46.176449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-15T05:17:48.403406Z digest=sha256:e98aea62b5ffc8c819ccaaf65b76e88d10ac82f6ec303b7861a4e20ce7886b37

Observation 057ba5b3-7239-453d-aa50-9d73c6ab6b97 · inbound

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

ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Reference 29

Resolution
metadata mismatch
arxiv_id, observed 2026-07-04T09:49:44.829010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-06-26T09:22:55.731241Z digest=sha256:d652749f59c1986e23b5aa427d10bb943aa32cfe7a25f5133c6ce1bad150a63f