4 papers
TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning
Zhenan Wang, Yanzhe Wang, Meixuan Ren +8
In visually ambiguous manipulation such as detecting button click tactile feedback is often the sole source of ground truth. However, fusing tactile data poses a significant challe…
LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents
Boyu Chen, Zhengrong Yue, Siran Chen +4
Existing MLLMs encounter significant challenges in modeling the temporal context within long videos. Currently, mainstream Agent-based methods use external tools to assist a single…
CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models
Yiqi Zhu, Ziyue Wang, Can Zhang +2
Vision-Language Models (VLMs) have recently witnessed significant progress in visual comprehension. As the permitting length of image context grows, VLMs can now comprehend a broad…
A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
Zijun Liu, Yanzhe Zhang, Peng Li +2
Recent studies show that collaborating multiple large language model (LLM) powered agents is a promising way for task solving. However, current approaches are constrained by using…