2025 "sparse attention" Papers
9 papers found
FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
Xunhao Lai, Jianqiao Lu, Yao Luo et al.
ICLR 2025posterarXiv:2502.20766
51
citations
Kinetics: Rethinking Test-Time Scaling Law
Ranajoy Sadhukhan, Zhuoming Chen, Haizhong Zheng et al.
NeurIPS 2025posterarXiv:2506.05333
7
citations
LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions
Ravindran Kannan, Chiranjib Bhattacharyya, Praneeth Kacham et al.
ICLR 2025posterarXiv:2410.05462
1
citations
MagicPIG: LSH Sampling for Efficient LLM Generation
Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye et al.
ICLR 2025posterarXiv:2410.16179
62
citations
MoBA: Mixture of Block Attention for Long-Context LLMs
Enzhe Lu, Zhejun Jiang, Jingyuan Liu et al.
NeurIPS 2025spotlightarXiv:2502.13189
94
citations
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Kwanyoung Kim, Byeongsu Sim
ICCV 2025posterarXiv:2503.07677
1
citations
Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape
Ruichen Chen, Keith Mills, Liyao Jiang et al.
NeurIPS 2025oralarXiv:2505.22918
1
citations
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Shuo Yang, Haocheng Xi, Yilong Zhao et al.
NeurIPS 2025spotlightarXiv:2505.18875
31
citations
Transformers Learn Faster with Semantic Focus
Parikshit Ram, Kenneth Clarkson, Tim Klinger et al.
NeurIPS 2025posterarXiv:2506.14095