Papers

Filtered to sparse attention · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

32 upvotes · 27 JUL 2026 · Haopeng Li, Yitong Li, Junsong Chen et al.

This paper improves the efficiency of video generation by reducing the computational load of attention, a key bottleneck in diffusion transformers. Practitioners can benefit from the speedup achieved by Sol-Attn, which enables faster video generation and editing without compromising visual quality.

diffusion transformerssparse attentionvideo generationattention sparsificationproxy scores

Wonder: Video World Model Done Better

17 upvotes · 28 JUL 2026 · Jiacong Xu, Hanwen Jiang, Zhixin Shu et al.

This paper introduces Wonder, a system that can generate videos of a virtual world in real-time, allowing users to interact with and explore the environment. Practitioners in fields like video game development or virtual reality might care about this technology for its potential to create more immersive experiences.

video world modelsreal-time generationsparse attentioncamera conditioninggenerative models

FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation

8 upvotes · 17 JUL 2026 · Hao Liu, Chenghuan Huang, Ye Huang et al.

This paper develops a more efficient way to generate high-quality videos by balancing the workload across multiple GPUs during training, which can improve the performance of video generation models like those used in FVAttn. Practitioners in video generation and deep learning might care about this research because it can lead to faster and more efficient video generation models.

sparse attentionvideo generationdistributed trainingGPU parallelismload balancing