Real-Time Video Generation with Pyramid Attention Broadcast | Paper Citation Record

Observation e010d170-4e2b-4d2b-9aff-50ddd3b83e72 · inbound

PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference cites this paper.

PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference Real-Time Video Generation with Pyramid Attention Broadcast

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-24T01:18:42.451669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 068449c1-770e-4e67-ab01-2487027d9d06 · inbound

Movie Gen: A Cast of Media Foundation Models cites this paper.

Movie Gen: A Cast of Media Foundation Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:16:20.266812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cee3c71a-f9f1-4e0d-8d45-d9a4c857d519 · inbound

SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers cites this paper.

SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers Real-Time Video Generation with Pyramid Attention Broadcast

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T19:47:54.469023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce6e9dfb-a30d-44af-8c5d-c5d39ae81a75 · inbound

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study cites this paper.

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study Real-Time Video Generation with Pyramid Attention Broadcast

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T18:47:22.621472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46fe8d79-f749-4c89-9565-3b448c4eb1f2 · inbound

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

Importance-Based Token Merging for Efficient Image and Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 116

Resolution: unresolved; no resolver link, observed 2026-08-12T14:24:43.840731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672a973f-3971-48f5-8845-8eee16213a04 · inbound

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient cites this paper.

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient Real-Time Video Generation with Pyramid Attention Broadcast

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T12:06:01.203068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f632e71-6d94-470b-b1bc-91110b680118 · inbound

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model cites this paper.

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model Real-Time Video Generation with Pyramid Attention Broadcast

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T10:35:25.317720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75e8dcef-507e-4fe9-83d0-8d63de4a5069 · inbound

TinyFusion: Diffusion Transformers Learned Shallow cites this paper.

TinyFusion: Diffusion Transformers Learned Shallow Real-Time Video Generation with Pyramid Attention Broadcast

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T04:40:19.618708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b70e556b-5831-460d-97b5-4b46cd980b7c · inbound

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

HunyuanVideo: A Systematic Framework For Large Video Generative Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 101

Resolution: verified exact; arxiv_id, observed 2026-05-23T07:42:43.448393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 073c8912-cab0-4b02-b246-79031ed54629 · inbound

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration cites this paper.

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration Real-Time Video Generation with Pyramid Attention Broadcast

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T14:44:17.681387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7d53d8-7a6c-42d1-91c4-4c58c204d380 · inbound

IDEA-Bench: How Far are Generative Models from Professional Designing? cites this paper.

IDEA-Bench: How Far are Generative Models from Professional Designing? Real-Time Video Generation with Pyramid Attention Broadcast

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T14:39:28.442561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0844f17-2e4e-47b9-b686-c70c90f1498c · inbound

Accelerating Diffusion Transformer via Error-Optimized Cache cites this paper.

Accelerating Diffusion Transformer via Error-Optimized Cache Real-Time Video Generation with Pyramid Attention Broadcast

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-09T20:53:59.507624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab7559ef-dab5-4f84-a086-e5305e5ff3ba · inbound

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

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity Real-Time Video Generation with Pyramid Attention Broadcast

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-09T14:35:10.694822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66cc62c7-cdbc-4ebc-a43a-82c162f99ce3 · inbound

Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile cites this paper.

Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile Real-Time Video Generation with Pyramid Attention Broadcast

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T16:36:00.856578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b35e6825-cabb-467f-9470-c2af8496806b · inbound

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate cites this paper.

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate Real-Time Video Generation with Pyramid Attention Broadcast

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T12:38:39.465001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f66b2f5-b20b-4c08-9b75-e089b1d87516 · inbound

Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios cites this paper.

Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios Real-Time Video Generation with Pyramid Attention Broadcast

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:35:46.800014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bc723fc-7583-491e-bcb1-8fd552838521 · inbound

dKV-Cache: The Cache for Diffusion Language Models cites this paper.

dKV-Cache: The Cache for Diffusion Language Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:11.838283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7657eb02-3f05-4b87-9b56-aa67632c1233 · inbound

SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation cites this paper.

SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:23:19.267997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30e5a746-e8e1-4266-af0e-8df43ff5936d · inbound

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression cites this paper.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Real-Time Video Generation with Pyramid Attention Broadcast

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.706471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7785b33f-34ad-4b07-b343-b05afabecfbd · inbound

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers cites this paper.

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers Real-Time Video Generation with Pyramid Attention Broadcast

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:18.510621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a29a636d-498e-411d-97d0-6021e513c632 · inbound

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation cites this paper.

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T11:14:10.807899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84245383-cba9-4a01-a43b-05d640fb7874 · inbound

DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving cites this paper.

DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving Real-Time Video Generation with Pyramid Attention Broadcast

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:06.557898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3980b98c-70c9-4aeb-8e45-b794432a471d · inbound

PromptTea: Let Prompts Tell TeaCache the Optimal Threshold cites this paper.

PromptTea: Let Prompts Tell TeaCache the Optimal Threshold Real-Time Video Generation with Pyramid Attention Broadcast

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:01:33.101681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edd3f45b-cc1b-4de1-9d62-6b5636f36a25 · inbound

EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models cites this paper.

EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:45.031105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef35527-f37a-4f1b-a32b-511092a18b0b · inbound

TaoCache: Structure-Maintained Video Generation Acceleration cites this paper.

TaoCache: Structure-Maintained Video Generation Acceleration Real-Time Video Generation with Pyramid Attention Broadcast

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:33:44.581158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1faab66-0305-46d0-a4c1-b0635b35f7ac · inbound

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers cites this paper.

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers Real-Time Video Generation with Pyramid Attention Broadcast

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T17:31:13.099733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c388957f-a811-4dc3-b526-d985494b933b · inbound

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models cites this paper.

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T17:42:59.655799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e0dc6b6-da1c-4072-aaba-7b008e3e1c19 · inbound

DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration cites this paper.

DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration Real-Time Video Generation with Pyramid Attention Broadcast

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T19:11:59.615094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b8c803f-53b2-4c72-bd44-bc0f096d354a · inbound

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching cites this paper.

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching Real-Time Video Generation with Pyramid Attention Broadcast

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T16:00:04.705327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 213073bc-1f5e-48e7-a2a7-c5985a481b39 · inbound

Training Agents Inside of Scalable World Models cites this paper.

Training Agents Inside of Scalable World Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:05:52.585310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation eaecef53-ef6a-4cd7-b6e1-7c7510dedc9a · inbound

Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space cites this paper.

Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space Real-Time Video Generation with Pyramid Attention Broadcast

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T22:12:45.658267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02255014-b988-4b05-a6a1-cc89ab91f82e · inbound

Transition Matching Distillation for Fast Video Generation cites this paper.

Transition Matching Distillation for Fast Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-03T10:35:06.656770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b01f8fe-0205-4c2f-9326-9a82cef5fa74 · inbound

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching cites this paper.

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching Real-Time Video Generation with Pyramid Attention Broadcast

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-16T07:30:44.419653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d78a80ee-8e15-4364-9189-f156b577fc84 · inbound

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation cites this paper.

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:48:15.800455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b0a3a65f-1623-4fba-8c91-6d93e22dcc3b · inbound

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

Efficient Video Diffusion Models: Advancements and Challenges Real-Time Video Generation with Pyramid Attention Broadcast

Reference 195

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:03:26.198899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation eb461fd8-b479-4d47-8b89-be873c7378a5 · inbound

LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference cites this paper.

LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference Real-Time Video Generation with Pyramid Attention Broadcast

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:56:05.102208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 12344ac0-8d9f-4568-9f14-9af0a6bd1d70 · inbound

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation cites this paper.

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:43:49.766913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1f827d4c-fafe-42bb-9bfa-b52346df6e5d · inbound

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

DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion Real-Time Video Generation with Pyramid Attention Broadcast

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:36:07.894784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f83863ed-fd8f-49ce-b954-9ff1cc1234e8 · inbound

Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment cites this paper.

Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment Real-Time Video Generation with Pyramid Attention Broadcast

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T22:16:50.598532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e5fdcba2-958b-4d91-99d8-f9350e9dce32 · inbound

Motion-Aware Caching for Efficient Autoregressive Video Generation cites this paper.

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

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:06:01.702813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

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

Motion-Aware Caching for Efficient Autoregressive Video Generation cites this paper.

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 2026-08-17T06:30:58.91139+00:00.

Observation c6299bef-1d0e-44fc-b694-a5a54f283cb3 · inbound

ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration cites this paper.

ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration Real-Time Video Generation with Pyramid Attention Broadcast

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:43.387273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6af77109-ee12-42cb-b6a4-fe3a47666843 · inbound

VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation cites this paper.

VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:00:22.465253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bbb4e3e7-53d3-4596-8fa5-d6c474d32df8 · inbound

PARE: Pruning and Adaptive Routing for Efficient Video Generation cites this paper.

PARE: Pruning and Adaptive Routing for Efficient Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:13:48.832340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c68db5b6-5e09-463e-89ce-b040355a21c6 · inbound

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models cites this paper.

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:26:00.150469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 842281c1-60fc-4780-8e29-aba43cb49549 · inbound

Fewer, Better Frames: A Compute-Normalized Proof of Concept for Coherence-First World-Model Rendering with Model-Guided FSR4 Frame Generation cites this paper.

Fewer, Better Frames: A Compute-Normalized Proof of Concept for Coherence-First World-Model Rendering with Model-Guided FSR4 Frame Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-06-30T22:25:06.902572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cac81f9f-2acf-4e1a-9bf3-2a3ee63dd643 · inbound

RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling cites this paper.

RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling Real-Time Video Generation with Pyramid Attention Broadcast

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:26:56.756036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9d7d5444-7977-45f9-b025-9ba02baa1513 · inbound

Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation cites this paper.

Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:49:41.580040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 006a01c5-e1d3-44b8-b593-fc918bc26bab · inbound

OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models cites this paper.

OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:45:39.499644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 01887001-f51b-4e49-9ffa-6418cc2abb74 · inbound

ACID: Adaptive Caching for vIDeo generation cites this paper.

ACID: Adaptive Caching for vIDeo generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T06:40:17.660809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad384f00-2226-461c-99bf-5e69ebc8d22a · inbound

Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations cites this paper.

Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations Real-Time Video Generation with Pyramid Attention Broadcast

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-02T03:51:53.756730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dafe89c-a4cc-4487-9aa1-3e3919d928b3 · inbound

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse cites this paper.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Real-Time Video Generation with Pyramid Attention Broadcast

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:29.268782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64fb3c06-070c-44dc-bdec-10ebe130ec50 · inbound

JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models cites this paper.

JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-01T17:41:03.776113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d1f7ac-5ffe-4123-aad8-7aaf29ac69ac · inbound

Importance-Aware OBS Pruning for Diffusion Models cites this paper.

Importance-Aware OBS Pruning for Diffusion Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-01T10:59:55.303447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e2b6289-1421-4c2c-9b1b-867bc50fb1c8 · inbound

CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion cites this paper.

CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion Real-Time Video Generation with Pyramid Attention Broadcast

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T03:30:26.623742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c537c2-74be-4508-8119-22a9dbd5111e · inbound

OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models cites this paper.

OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models Real-Time Video Generation with Pyramid Attention Broadcast

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-30T10:48:16.511850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3458ba6d-8838-4a3d-b5e5-9e1b77ccafd6 · inbound

MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention cites this paper.

MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention Real-Time Video Generation with Pyramid Attention Broadcast

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T16:32:51.924964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48a79f2f-3cef-4e21-8e90-78734aad181c · inbound

EchoCache: Energy-Guided Cross-Modal Caching for Efficient Audio-Driven Video Generation cites this paper.

EchoCache: Energy-Guided Cross-Modal Caching for Efficient Audio-Driven Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T06:45:50.046478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fce78ba5-26da-44d5-a3a7-ff24274c5ae2 · inbound

Token Radius Attention for Efficient Video Generation cites this paper.

Token Radius Attention for Efficient Video Generation Real-Time Video Generation with Pyramid Attention Broadcast

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-04T06:03:07.410471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335452dc-9705-4d37-9bf0-6bf1cf147e36 · inbound

Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference cites this paper.

Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference Real-Time Video Generation with Pyramid Attention Broadcast

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-15T14:46:04.362474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a37a188b-8371-436b-a28c-e209c62bb7b9 · inbound

BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers Inference cites this paper.

BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers Inference Real-Time Video Generation with Pyramid Attention Broadcast

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T00:40:50.022316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers