ESTRA: Enabling Extreme Attention Sparsity for Training-Free Video Diffusion Acceleration
cs.CV
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
- PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers
- LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration
- Movie Gen: A Cast of Media Foundation Models
- Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas
- Wan: Open and Advanced Large-Scale Video Generative Models
- PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers
- VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillation
- PARE: Pruning and Adaptive Routing for Efficient Video Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs