activity
20242026
collaborators

6 papers

cs.LG2026

SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning

Yao-Hui Li, Zeyu Wang, Xin Li +7

Model-based reinforcement learning (MBRL) is sample-efficient but struggles in sparse reward settings. A critical bottleneck arises from the lack of informative gradients in sparse…

cs.CV2025

Motus: A Unified Latent Action World Model

Hongzhe Bi, Hengkai Tan, Shenghao Xie +13

While a general embodied agent must function as a unified system, current methods are built on isolated models for understanding, world modeling, and control. This fragmentation pr…

cs.CV2025

Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction

Juncheng Hu, Zijian Zhang, Zeyu Wang +3

Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on im…

cs.LG2025

Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning

Leiji Zhang, Zeyu Wang, Xin Li +1

Bisimulation metric has long been regarded as an effective control-related representation learning technique in various reinforcement learning tasks. However, in this paper, we ide…

cs.LG2025

Learning Fused State Representations for Control from Multi-View Observations

Zeyu Wang, Yao-Hui Li, Xin Li +3

Multi-View Reinforcement Learning (MVRL) seeks to provide agents with multi-view observations, enabling them to perceive environment with greater effectiveness and precision. Recen…

cs.RO2024

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

Qixiu Li, Yaobo Liang, Zeyu Wang +15

The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen…