most citedKARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems

2 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Fengze Yang, Bo Yu, Xuewen Luo +2

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-…