2 papers
cs.CV2026
Think in Sets for Streaming Video Token Compression
Moxu Duan, Jingwen Fu, Yuwang Wang
Streaming VideoLLMs process frames causally while visual tokens grow continuously, making compression essential for controlling prefilling latency and memory. Existing training-fre…
cs.AI2026
Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning
Lesong Tao, Yifei Wang, Haodong Jing +4
Value factorization, a popular paradigm in MARL, faces significant theoretical and algorithmic bottlenecks: its tendency to converge to suboptimal solutions remains poorly understo…