Chengmei Yang

Longitudinal medical visual reasoning is critically underexplored, with existing models failing to grasp temporal nuances, as evidenced by their poor performance on the new LoMeVQA benchmark.

MLLMs can slash 68% of their FLOPs with minimal accuracy loss by pruning visual tokens at the "Entropy Collapse Layer"—where information content plummets—using a new matrix-entropy-guided method.