VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning 事件

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning arXiv:2605.31457v1 Announce Type: new Abstract: With the rapid advancement of large multimodal models (LMMs), inference-time overhead has become a key bottleneck for real-world deployment. Existing methods typically prune visual tokens at prefill, assuming the required visual evidence remains static during reasoning. However, we empirically show that visual evidence is strongly step-dependent: only a sparse subset of visual