Showing 2026Show all
3 papers · 1 filter
cs.AI2026
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
Yu Zhao, Zekun Zhang, Fan Jiang +9
Long chain-of-thought (CoT) reasoning models such as DeepSeek-R1 keep lengthening their inference chains under test-time scaling, yet standard self-attention incurs quadratic cost…
cs.AI2026
OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows
Ruiting Dai, Zheyu Wang, Haoyu Yang +6
Data incompleteness severely impedes the reliability of multimodal systems. Existing reconstruction methods face distinct bottlenecks: conventional parametric/generative models are…
cs.CV2026
Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
Yuxi Liu, Yipeng Hu, Zekun Zhang +2
While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent…