CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models 事件

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models arXiv:2605.28115v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face severe memory and latency bottlenecks due to high-resolution visual tokens. While current token reduction methods theoretically save FLOPs, post-hoc pruning introduces structural overhead, failing to yield proportional wall-clock acceleration. However, enforcing a contiguous compact pathway risks geometric disorientation and loss of fine-