VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding 事件

VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding arXiv:2605.25952v1 Announce Type: new Abstract: Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue and reliance on the heuristic pruning strategy with coarse attention alignment incurs a bottleneck on the information