5 papers
ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models
Zuojin Tang, Haoyun Liu, Xinyuan Chang +11
Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evidence of how the physical world…
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Zuojin Tang, Shengchao Yuan, Xiaoxin Bai +4
Vision-language-action (VLA) models can use visual prediction to anticipate future states, but dense visual features make the generative sequence grow with the number of camera vie…
Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors
Lang Feng, Jiahao Lin, Dong Xing +3
Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing…
Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree
Lang Feng, Pengjie Gu, Bo An +1
Diffusion planners have shown promise in handling long-horizon and sparse-reward tasks due to the non-autoregressive plan generation. However, their inherent stochastic risk of gen…
FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility
Lang Feng, Dong Xing, Junru Zhang +1
Existing multi-agent PPO algorithms lack compatibility with different types of parameter sharing when extending the theoretical guarantee of PPO to cooperative multi-agent reinforc…