Xiao Ma

12

Papers

876

Total Citations

Papers (12)

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

Safety Alignment Should be Made More Than Just a Few Tokens Deep

Flow-Based Policy for Online Reinforcement Learning

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

NeurIPS 2025arXiv

CODA: Repurposing Continuous VAEs for Discrete Tokenization

Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation

Imitation Learning As State Matching via Differentiable Physics

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Mutual Information Regularized Offline Reinforcement Learning

InsActor: Instruction-driven Physics-based Characters

Efficient Diffusion Policies For Offline Reinforcement Learning