Motion-Aware Caching for Efficient Autoregressive Video Generation | Paper Citation Record

Observation db32befb-0d8d-4588-87c8-6482658fc18e · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.896056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3930bfdd-8942-4184-99aa-9b2f52e4a6b2 · outbound

This paper cites Video generation models as world simulators.OpenAI Blog, 1(8):1.

Motion-Aware Caching for Efficient Autoregressive Video Generation Video generation models as world simulators.OpenAI Blog, 1(8):1

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.898588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eb9701d3-7ff5-4407-b7a7-9db24b731904 · outbound

This paper cites Dicache: Let diffusion model determine its own cache.

Motion-Aware Caching for Efficient Autoregressive Video Generation Dicache: Let diffusion model determine its own cache

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.930970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2fe5a6a5-c74c-41ff-b21e-77e5e2315049 · outbound

This paper cites Diffusion forcing: Next-token prediction meets full-sequence diffusion.Advancesin Neural Information Processing Systems, 37:24081–24125.

Motion-Aware Caching for Efficient Autoregressive Video Generation Diffusion forcing: Next-token prediction meets full-sequence diffusion.Advancesin Neural Information Processing Systems, 37:24081–24125

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.888297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 99424ea2-498f-4655-83a5-586b3c7514b9 · outbound

This paper cites SkyReels-V2: Infinite-length Film Generative Model.

Motion-Aware Caching for Efficient Autoregressive Video Generation SkyReels-V2: Infinite-length Film Generative Model

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.947598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e64af7d8-3a35-41e5-b244-bd06d9fe164f · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.921424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 78123c58-eafa-44a6-afcb-ee7e0363980e · outbound

This paper cites E2net: Excitative- expansile learning for weakly supervised object localization.

Motion-Aware Caching for Efficient Autoregressive Video Generation E2net: Excitative- expansile learning for weakly supervised object localization

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.919334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f1b582b5-469f-4dff-8efd-b827c36378f7 · outbound

This paper cites Lctr: On awakening the local continuity of transformer for weakly supervised object localization.

Motion-Aware Caching for Efficient Autoregressive Video Generation Lctr: On awakening the local continuity of transformer for weakly supervised object localization

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.892211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a234dbd7-fb63-4df9-bd6b-de89dc38214c · outbound

This paper cites Category-aware allocation transformer for weakly supervised object localization.

Motion-Aware Caching for Efficient Autoregressive Video Generation Category-aware allocation transformer for weakly supervised object localization

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.916183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 56033a54-24fb-40fc-abc2-d7f4989c6983 · outbound

This paper cites Adaptive zone learning for weakly supervised object localization.IEEE Transactions on Neural Networks and Learning Systems, 36(4):7211–7224.

Motion-Aware Caching for Efficient Autoregressive Video Generation Adaptive zone learning for weakly supervised object localization.IEEE Transactions on Neural Networks and Learning Systems, 36(4):7211–7224

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.908696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4b1eca82-c7fe-4f22-ad7a-846c868ade13 · outbound

This paper cites Clip-driven transformer for weakly supervised object localization.IEEE Transactions on Pattern Analysis and Machine Intelligence.

Motion-Aware Caching for Efficient Autoregressive Video Generation Clip-driven transformer for weakly supervised object localization.IEEE Transactions on Pattern Analysis and Machine Intelligence

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.905199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4086274-bace-4f17-b2f8-e1f0284a1cd4 · outbound

This paper cites Bwcache: Accelerating video diffusion transformers through block-wise caching.

Motion-Aware Caching for Efficient Autoregressive Video Generation Bwcache: Accelerating video diffusion transformers through block-wise caching

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.915809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c2f1e0ec-12c9-459a-ac92-6bb3a2cbdbc5 · outbound

This paper cites Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers.

Motion-Aware Caching for Efficient Autoregressive Video Generation Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.953112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7158db05-0736-469a-85fc-32fb20ba3bcd · outbound

This paper cites Mdreid: Modality-decoupled learning for any-to-any multi-modal object re-identification.

Motion-Aware Caching for Efficient Autoregressive Video Generation Mdreid: Modality-decoupled learning for any-to-any multi-modal object re-identification

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.936641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 271c8514-27e6-41f4-b81f-a6abfd8dde50 · outbound

This paper cites Multi-modal object re-identification via sparse mixture-of- experts.

Motion-Aware Caching for Efficient Autoregressive Video Generation Multi-modal object re-identification via sparse mixture-of- experts

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.931039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3c8f16c5-1af2-4f8a-91c4-3b2fac20e7fe · outbound

This paper cites Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey.

Motion-Aware Caching for Efficient Autoregressive Video Generation Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.925578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 943613f0-7593-4027-94e2-e9dd7daa0396 · outbound

This paper cites Magicdrive-v2: High-resolution long video generation for autonomous driving with adaptive control.

Motion-Aware Caching for Efficient Autoregressive Video Generation Magicdrive-v2: High-resolution long video generation for autonomous driving with adaptive control

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.928370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 672af5f5-38b8-4ece-957e-8a2b1951cef6 · outbound

This paper cites Seedance 1.0: Exploring the Boundaries of Video Generation Models.

Motion-Aware Caching for Efficient Autoregressive Video Generation Seedance 1.0: Exploring the Boundaries of Video Generation Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.960186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dceb1060-3fe8-4255-be2e-dda5054d3509 · outbound

This paper cites Image quality metrics: Psnr vs.

Motion-Aware Caching for Efficient Autoregressive Video Generation Image quality metrics: Psnr vs

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.937125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 966beaf0-7c13-451c-890a-214f194ab4c5 · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation Vbench: Comprehensive benchmark suite for video generative models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.901849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1520e239-bcc9-4167-81ed-2d93e7f09488 · outbound

This paper cites Ir evaluation methods for retrieving highly relevant documents.

Motion-Aware Caching for Efficient Autoregressive Video Generation Ir evaluation methods for retrieving highly relevant documents

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.911731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9ceddbd8-4135-4a62-847a-d24978c56410 · outbound

This paper cites Adaptive caching for faster video generation with diffusion transformers.

Motion-Aware Caching for Efficient Autoregressive Video Generation Adaptive caching for faster video generation with diffusion transformers

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.925517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c5ec4900-5ae2-406e-8de2-a0f99560fbeb · outbound

This paper cites Elucidating the design space of diffusion-based generative models.

Motion-Aware Caching for Efficient Autoregressive Video Generation Elucidating the design space of diffusion-based generative models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.949659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8a1b4af7-5e03-41ee-ac3a-22fb0a578258 · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.942409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ea025c3a-bee0-40fb-ad9a-8ab7a5636bf2 · outbound

This paper cites Rle: A unified perspective of data augmentation for cross-spectral re-identification.Advances in Neural Information Processing Systems, 37:126977–126996.

Motion-Aware Caching for Efficient Autoregressive Video Generation Rle: A unified perspective of data augmentation for cross-spectral re-identification.Advances in Neural Information Processing Systems, 37:126977–126996

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.903214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 89e528a4-3bc3-4217-b251-aeb5a2a72668 · outbound

This paper cites Find: A simple yet effective baseline for diffusion- generated image detection.

Motion-Aware Caching for Efficient Autoregressive Video Generation Find: A simple yet effective baseline for diffusion- generated image detection

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.946911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d6ea5eb1-0e6b-4391-a349-64db6df93854 · outbound

This paper cites Apoavatar: Expressive audio-driven avatar generation via refocused audio-pose priors.

Motion-Aware Caching for Efficient Autoregressive Video Generation Apoavatar: Expressive audio-driven avatar generation via refocused audio-pose priors

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.940845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e182a9c-d53d-428a-94d3-75ca5755e7b2 · outbound

This paper cites An end-to-end scene text detector with dynamic attention.

Motion-Aware Caching for Efficient Autoregressive Video Generation An end-to-end scene text detector with dynamic attention

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.933977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1c053e8b-6740-4bac-b439-3b8d27d6a235 · outbound

This paper cites A dual-path transformer network for scene text detection.

Motion-Aware Caching for Efficient Autoregressive Video Generation A dual-path transformer network for scene text detection

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.922084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b8a3eea2-5658-4149-86df-2467162743fa · outbound

This paper cites Pair-id: A dual modal framework for identity preserving image generation.IEEE Signal Processing Letters, 31:2715–2719.

Motion-Aware Caching for Efficient Autoregressive Video Generation Pair-id: A dual modal framework for identity preserving image generation.IEEE Signal Processing Letters, 31:2715–2719

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.943687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3298242d-5766-44fc-8862-1781e1b3eb54 · outbound

This paper cites Difftv: Identity-preserved thermal-to-visible face translation via feature alignment and dual-stage conditions.

Motion-Aware Caching for Efficient Autoregressive Video Generation Difftv: Identity-preserved thermal-to-visible face translation via feature alignment and dual-stage conditions

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.952536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1aae08bf-0b24-4b94-9386-d843e71badc8 · outbound

This paper cites Flow Matching for Generative Modeling.

Motion-Aware Caching for Efficient Autoregressive Video Generation Flow Matching for Generative Modeling

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.920458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2672b17f-b1d6-4318-8998-6ff1ea2e607d · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation Timestep embedding tells: It’s time to cache for video diffusion model

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.790916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7dbf68a4-0b9a-4043-8f39-5bcb49efbffa · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.790547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 15f88856-ccec-4472-8c61-d599eb844574 · outbound

This paper cites Speca: Accelerating diffusion transformers with speculative feature caching.

Motion-Aware Caching for Efficient Autoregressive Video Generation Speca: Accelerating diffusion transformers with speculative feature caching

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.874725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cb840779-20bc-4a8c-a259-407673469531 · outbound

This paper cites Token caching for diffusion transformer acceleration.

Motion-Aware Caching for Efficient Autoregressive Video Generation Token caching for diffusion transformer acceleration

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.754855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3a709a7a-8672-4711-aa65-34fd25f5b6de · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation Latte: Latent Diffusion Transformer for Video Generation

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.901356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fd5e47f3-940d-469e-ad32-68c318977958 · outbound

This paper cites Ompq: Orthogonal mixed precision quantization.

Motion-Aware Caching for Efficient Autoregressive Video Generation Ompq: Orthogonal mixed precision quantization

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.877612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f74eeee5-112d-440e-89ab-26a0e003790d · outbound

This paper cites Solving oscillation problem in post-training quantization through a theoretical perspective.

Motion-Aware Caching for Efficient Autoregressive Video Generation Solving oscillation problem in post-training quantization through a theoretical perspective

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.886808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c3561847-6032-44bf-b86a-fcc7e660e178 · outbound

This paper cites AffineQuant: Affine Transformation Quantization for Large Language Models.

Motion-Aware Caching for Efficient Autoregressive Video Generation AffineQuant: Affine Transformation Quantization for Large Language Models

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.936510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d28ad9d3-d7fe-4a60-8af6-a7ce6aeaea59 · outbound

This paper cites Outlier-aware slicing for post-training quantization in vision transformer.

Motion-Aware Caching for Efficient Autoregressive Video Generation Outlier-aware slicing for post-training quantization in vision transformer

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.868048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0fb2d52e-4f6f-4e74-8b80-5fd992b00411 · outbound

This paper cites Flow caching for autoregressive video generation.

Motion-Aware Caching for Efficient Autoregressive Video Generation Flow caching for autoregressive video generation

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.819366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b6d18226-6221-4d49-af70-795890db1c78 · outbound

This paper cites Complementary RL: Towards Efficient Experience-Driven Agent Learning.

Motion-Aware Caching for Efficient Autoregressive Video Generation Complementary RL: Towards Efficient Experience-Driven Agent Learning

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-06-30T02:15:38.360582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a2b673c4-53ee-4638-97d9-e4b174070a20 · outbound

This paper cites When Does Sparsity Mitigate the Curse of Depth in LLMs.

Motion-Aware Caching for Efficient Autoregressive Video Generation When Does Sparsity Mitigate the Curse of Depth in LLMs

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T02:15:38.277012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7b10d252-d2ee-4ad9-bf42-6b3cc0a78412 · outbound

This paper cites Scalable diffusion models with transformers.

Motion-Aware Caching for Efficient Autoregressive Video Generation Scalable diffusion models with transformers

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.861250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 51fd0951-e744-4f08-9daf-4557e8e93091 · outbound

This paper cites Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k.

Motion-Aware Caching for Efficient Autoregressive Video Generation Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:09:39.930389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation efa01418-a84a-491a-92a3-a07c54616757 · outbound

This paper cites Ertacache: Error rectification and timesteps adjustment for efficient diffusion.

Motion-Aware Caching for Efficient Autoregressive Video Generation Ertacache: Error rectification and timesteps adjustment for efficient diffusion

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.749703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1e7ed50e-e777-4fdf-bf6e-e2798d5c7383 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Motion-Aware Caching for Efficient Autoregressive Video Generation Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.866738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 272ed6cd-17f6-4ef0-9a0a-af1e5ced0c32 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.

Motion-Aware Caching for Efficient Autoregressive Video Generation U-net: Convolutional networks for biomedical image segmentation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.864690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8f5deb06-2fe8-4cdf-9c4a-d961be40bc97 · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.Advancesin neural information processing systems, 35:36479–36494.

Motion-Aware Caching for Efficient Autoregressive Video Generation Photorealistic text-to-image diffusion models with deep language understanding.Advancesin neural information processing systems, 35:36479–36494

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.871595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8464736e-39e8-4bc1-9145-d9d16d4bc7a5 · outbound

This paper cites FORA: Fast-Forward Caching in Diffusion Transformer Acceleration.

Motion-Aware Caching for Efficient Autoregressive Video Generation FORA: Fast-Forward Caching in Diffusion Transformer Acceleration

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.873021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 77184a8d-7117-4fd2-b3d1-7d350e105790 · outbound

This paper cites TR-DQ: Time-Rotation Diffusion Quantization.

Motion-Aware Caching for Efficient Autoregressive Video Generation TR-DQ: Time-Rotation Diffusion Quantization

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.860305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d97d8e3b-0611-4377-b16b-1e8115f2458e · outbound

This paper cites History-Guided Video Diffusion.

Motion-Aware Caching for Efficient Autoregressive Video Generation History-Guided Video Diffusion

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:00:14.880011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dc2eff0a-a3e4-4a88-8905-304675b4c807 · outbound

This paper cites Diffusionfake: Enhancing generalization in deepfake detection via guided stable diffusion.Advances in Neural Information Processing Systems, 37:101474–101497.

Motion-Aware Caching for Efficient Autoregressive Video Generation Diffusionfake: Enhancing generalization in deepfake detection via guided stable diffusion.Advances in Neural Information Processing Systems, 37:101474–101497

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.880747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c59e2262-922e-48b8-9d1e-4b6d8b98681a · outbound

This paper cites Continual face forgery detection via historical distribution preserving.International Journal of Computer Vision, 133(3):1067–1084.

Motion-Aware Caching for Efficient Autoregressive Video Generation Continual face forgery detection via historical distribution preserving.International Journal of Computer Vision, 133(3):1067–1084

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.884111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a81a0fed-0a1d-4244-b75e-ca6bfbaa75e7 · outbound

This paper cites Towards general visual-linguistic face forgery detection.

Motion-Aware Caching for Efficient Autoregressive Video Generation Towards general visual-linguistic face forgery detection

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.891003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 72c6487e-0e81-4878-866b-c413535d7809 · outbound

This paper cites When ai settles down: Late-stage stability as a signature of ai-generated text detection.

Motion-Aware Caching for Efficient Autoregressive Video Generation When ai settles down: Late-stage stability as a signature of ai-generated text detection

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.926110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b11154f8-418f-4adc-b4f8-493eee73e682 · outbound

This paper cites Minimizing mismatch risk: A prototype-based routing framework for zero-shot llm-generated text detection.

Motion-Aware Caching for Efficient Autoregressive Video Generation Minimizing mismatch risk: A prototype-based routing framework for zero-shot llm-generated text detection

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.830833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ebff62f9-0c04-4fb8-93fa-d0b166fccf48 · outbound

This paper cites Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search.

Motion-Aware Caching for Efficient Autoregressive Video Generation Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.931364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f1ec5648-4f20-4e3f-9341-f3eefa6ac2c6 · outbound

This paper cites MAGI-1: Autoregressive Video Generation at Scale.

Motion-Aware Caching for Efficient Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.915489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 11f5bd98-231c-4a25-942a-3a4907993e42 · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation Wan: Open and Advanced Large-Scale Video Generative Models

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.841117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 615db9b9-6684-426f-a23d-28273863232f · outbound

This paper cites Multi-kernel neural network sliding mode control for permanent magnet linear synchronous motors.IEEE Access, 9:57385–57392.

Motion-Aware Caching for Efficient Autoregressive Video Generation Multi-kernel neural network sliding mode control for permanent magnet linear synchronous motors.IEEE Access, 9:57385–57392

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.865494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9d31e02a-c09c-4c69-aa2e-b6a106a50e12 · outbound

This paper cites Dlf: Disentangled-language-focused multimodal sentiment analysis.

Motion-Aware Caching for Efficient Autoregressive Video Generation Dlf: Disentangled-language-focused multimodal sentiment analysis

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.861689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 66d1325d-e8ab-41a3-9169-f8b067018d50 · outbound

This paper cites From models to systems: A comprehensive survey of efficient multimodal learning.

Motion-Aware Caching for Efficient Autoregressive Video Generation From models to systems: A comprehensive survey of efficient multimodal learning

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.869455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 07e066dc-9160-4ff8-b9ac-f107f7adc2ce · outbound

This paper cites A theoretical analysis of ndcg type ranking measures.

Motion-Aware Caching for Efficient Autoregressive Video Generation A theoretical analysis of ndcg type ranking measures

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.872234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ddac4294-b064-45ec-a069-17f8e4393fd7 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612.

Motion-Aware Caching for Efficient Autoregressive Video Generation Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.875385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 76fc8e1d-58a8-490a-bdc7-07b4fc7f01f9 · outbound

This paper cites Panacea: Panoramic and controllable video generation for autonomous driving.

Motion-Aware Caching for Efficient Autoregressive Video Generation Panacea: Panoramic and controllable video generation for autonomous driving

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.881223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dc10b010-93ae-4a76-ac12-35a31c70e6fa · outbound

This paper cites Motioncanvas: Cinematic shot design with controllable image-to-video generation.

Motion-Aware Caching for Efficient Autoregressive Video Generation Motioncanvas: Cinematic shot design with controllable image-to-video generation

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.858266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c49ed621-35ca-47c0-b706-40d225f65f5e · outbound

This paper cites An enhanced differential evolution algorithm with a new oppositional-mutual learning strategy.Neurocomputing, 435:162–175.

Motion-Aware Caching for Efficient Autoregressive Video Generation An enhanced differential evolution algorithm with a new oppositional-mutual learning strategy.Neurocomputing, 435:162–175

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.854948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f471ac1a-d944-4f9c-9b07-9550474a8879 · outbound

This paper cites Veta-dit: Variance-equalized and temporally adaptive quantization for efficient 4-bit diffusion transformers.

Motion-Aware Caching for Efficient Autoregressive Video Generation Veta-dit: Variance-equalized and temporally adaptive quantization for efficient 4-bit diffusion transformers

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.848399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b4e3eb74-0b54-48ea-a94e-d01ad14382b7 · outbound

This paper cites LongLive: Real-time Interactive Long Video Generation.

Motion-Aware Caching for Efficient Autoregressive Video Generation LongLive: Real-time Interactive Long Video Generation

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.815186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dbd3fdbe-6ba4-4db5-93cb-4158ccc7194d · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.854714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8d744cff-7f74-4b00-898c-f66105b08146 · outbound

This paper cites From slow bidirectional to fast autoregressive video diffusion models.

Motion-Aware Caching for Efficient Autoregressive Video Generation From slow bidirectional to fast autoregressive video diffusion models

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.851677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a11e21c6-df34-477d-85e4-f8fd8eead64a · outbound

This paper cites Ab-cache: Training-free acceleration of diffusion models via adams-bashforth cached feature reuse.

Motion-Aware Caching for Efficient Autoregressive Video Generation Ab-cache: Training-free acceleration of diffusion models via adams-bashforth cached feature reuse

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.844511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b9995ed7-6bec-45c7-90c1-cf09f14b1fbd · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

Motion-Aware Caching for Efficient Autoregressive Video Generation The unreasonable effectiveness of deep features as a perceptual metric

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.835985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 97e9efbb-e1b2-4173-a1f3-6df3ad47d142 · outbound

This paper cites HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize.

Motion-Aware Caching for Efficient Autoregressive Video Generation HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-08-05T01:34:17.852905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0d2b3cef-452a-46a7-9186-d894336ea830 · outbound

This paper cites ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation.

Motion-Aware Caching for Efficient Autoregressive Video Generation ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.890022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e019637-7fa0-41b1-8de5-06c55e604d95 · outbound

This paper cites Real-Time Video Generation with Pyramid Attention Broadcast.

Motion-Aware Caching for Efficient Autoregressive Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.942745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f06a69c2-3c26-4748-ba8c-5bac23da13de · outbound

This paper cites An Information Theory-inspired Strategy for Automatic Network Pruning.

Motion-Aware Caching for Efficient Autoregressive Video Generation An Information Theory-inspired Strategy for Automatic Network Pruning

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.737741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a8ca8bb5-64c5-4750-9d5c-dab5ed3b5062 · outbound

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

Motion-Aware Caching for Efficient Autoregressive Video Generation Open-Sora: Democratizing Efficient Video Production for All

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.840814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9273b2cf-0343-479c-a65f-9aa3386c5671 · outbound

This paper cites Compute only 16 tokens in one timestep: Accelerating diffusion transformers with cluster-driven feature caching.

Motion-Aware Caching for Efficient Autoregressive Video Generation Compute only 16 tokens in one timestep: Accelerating diffusion transformers with cluster-driven feature caching

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.847065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 30f458b9-78bc-4ebe-84f4-03fff994b02b · outbound

This paper cites I&s-vit: An inclusive & stable method for pushing the limit of post-training vits quantization.

Motion-Aware Caching for Efficient Autoregressive Video Generation I&s-vit: An inclusive & stable method for pushing the limit of post-training vits quantization

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.824605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a1698a37-f4e5-48de-9f87-0ee276d9ea64 · outbound

This paper cites Erq: Error reduction for post-training quantization of vision transformers.

Motion-Aware Caching for Efficient Autoregressive Video Generation Erq: Error reduction for post-training quantization of vision transformers

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.832564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6496700a-463e-4e35-aa8b-accc70b61c3c · outbound

This paper cites Towards accurate post-training quantization of vision transformers via error reduction.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4):2676–2692.

Motion-Aware Caching for Efficient Autoregressive Video Generation Towards accurate post-training quantization of vision transformers via error reduction.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4):2676–2692

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.815482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bf14914a-06fc-4b58-9ffe-7e372814964c · outbound

This paper cites Test-time iterative error correction for efficient diffusion models.

Motion-Aware Caching for Efficient Autoregressive Video Generation Test-time iterative error correction for efficient diffusion models

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.792348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 216a46f5-5ffb-4531-85b5-57f9de549eb8 · outbound

This paper cites Ec-darts: inducing equalized and consistent optimization into darts.

Motion-Aware Caching for Efficient Autoregressive Video Generation Ec-darts: inducing equalized and consistent optimization into darts

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.819659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 37aa3a07-a6a1-45c4-99d8-00921818f720 · outbound

This paper cites Training- free transformer architecture search.

Motion-Aware Caching for Efficient Autoregressive Video Generation Training- free transformer architecture search

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.824432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5ee992ff-47af-48a4-9eaf-8bec97733616 · outbound

This paper cites Training-free transformer architecture search with zero-cost proxy guided evolution.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(10):6525–6541.

Motion-Aware Caching for Efficient Autoregressive Video Generation Training-free transformer architecture search with zero-cost proxy guided evolution.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(10):6525–6541

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T07:19:50.810849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 67e0cda4-9b18-41f4-a08b-eb2378fc6562 · outbound

This paper cites Accelerating Diffusion Transformers with Token-wise Feature Caching.

Motion-Aware Caching for Efficient Autoregressive Video Generation Accelerating Diffusion Transformers with Token-wise Feature Caching

Reference 89

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:19:49.847116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers