Donglin Wang

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denosing Diffusion Process

Openhelix: Empirical Analysis of Dual-System VLA Models for Robotic Manipulation

Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning

Video Language Models are Human-Aligned Evaluators for Text to Motion Generation

RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models

NFPO: Stabilized Policy Optimization of Normalizing Flow for Robotic Policy Learning

Unraveling Max-Return Sequence Modeling via Return Consistency

VLA-RFT: Vision-Language-Action Reinforcement Fine-Tuning with Verified Rewards in World Simulators

CEED-VLA: Consistency Vision-language-action Model with Early-exit Decoding

Enhancing Adversarial Transferability via Component-Wise Transformation

Revisiting Maximum Mean Discrepancy via Diffusion Behavior Policy in Offline RL: A Mode-Seeking Perspective

Humanoid-R0: Bridging Text-to-Motion Generation and Physical Deployment via RL

Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation

Boundary-to-Region Supervision for Offline Safe Reinforcement Learning

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport

Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation

GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation

Goal-conditioned Reinforcement Learning with Subgoals Generated from Relabeling

Memory-Efficient Algorithm Distillation for In-context Reinforcement Learning

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

Decoupled Offline to Online finetuning via Dynamics Model

Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning

Distribution Corrected Estimation via Adversarial Density Weighted Regression

Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning

Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration

Revisiting the Design Choices in Max-Return Sequence Modeling

Bridging the Gap Beteween SL and TD Learning via Q-conditioned maximization