VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning

ArXi:2605.31457v1 Announce Type: new 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 tokens is critical at each decoding step, and the critical set evolves across reasoning.