Xiao Ma

papers

1,900

total citations

papers (12)

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

CVPR 2024arXiv

110

citations

InsActor: Instruction-driven Physics-based Characters

NEURIPS 2023arXiv

citations

Flow-Based Policy for Online Reinforcement Learning

NEURIPS 2025arXiv

citations

Mutual Information Regularized Offline Reinforcement Learning

NEURIPS 2023arXiv

citations

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

AAAI 2024arXiv

citations

CODA: Repurposing Continuous VAEs for Discrete Tokenization

ICCV 2025arXiv

citations

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

NEURIPS 2025arXiv

citations

Imitation Learning As State Matching via Differentiable Physics

CVPR 2023

citations

Xiao Ma

papers (12)

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

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

Efficient Diffusion Policies For Offline Reinforcement Learning

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

InsActor: Instruction-driven Physics-based Characters

Flow-Based Policy for Online Reinforcement Learning

Mutual Information Regularized Offline Reinforcement Learning

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

CODA: Repurposing Continuous VAEs for Discrete Tokenization

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

Imitation Learning As State Matching via Differentiable Physics

papers (12)

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

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

Efficient Diffusion Policies For Offline Reinforcement Learning

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

InsActor: Instruction-driven Physics-based Characters

Flow-Based Policy for Online Reinforcement Learning

Mutual Information Regularized Offline Reinforcement Learning

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

CODA: Repurposing Continuous VAEs for Discrete Tokenization

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

Imitation Learning As State Matching via Differentiable Physics