524 citations · 855 across the 19 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.CV2026
PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing
Peng Xu, Haoran Lin, Wanjun Jia +4
Vision-Language-Action (VLA) policies have shown promising performance in language-conditioned robotic manipulation. However, most existing VLA systems rely on conventional perspec…
cs.LG2026
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
Peng Xu, Sijia Chen, Junzhuo Li +1
Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ti…
cs.CV2026
Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
Haiyang Yan, Hongyun Zhou, Peng Xu +2
Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high informati…