DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Harbin Institute of Technology（哈尔滨工业大学）；ShanghaiTech University（上海科技大学）；Shanghai Institute of Technical Physics, CAS（中国科学院上海技术物理研究所）
Vision-Language-Action (VLA) models that encode actions using a discrete tokenization scheme have been widely adopted for robotic manipulation, but existing decoding paradigms remain fundamentally limited. Whether actions are decoded sequentially by autoregressive VLAs or in parallel by discrete diffusion VLAs, once a token is generated, it is typically fixed and cannot be revised in subsequent iterations. Consequently, early token errors cannot be effectively corrected later. We propose DFM-VLA, a discrete flow matching VLA that iteratively refines action tokens. DFM-VLA models a token-level probability velocity field that dynamically updates the full action sequence across refinement iterations. We investigate two approaches to constructing the velocity field: an auxiliary velocity-head formulation and an embedding-guided formulation. To further improve prediction accuracy, we introduce a metric-aligned action tokenizer (MAAT) tailored to the coarse-to-fine nature of DFM, together with a two-stage decoding strategy. Extensive experiments on CALVIN, LIBERO, LIBERO-Plus, and real-world manipulation tasks demonstrate the effectiveness of our approach. Our project is available at https://chris1220313648.github.io/DFM-VLA/.
Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Westlake University（西交大学）；Zhejiang University（浙江大学）；Monash University（墨尔本大学）
Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA
Shanghai Jiao Tong University（上海交通大学）；Sharpa；Shanghai AI Lab（上海人工智能实验室）；Zhongguancun Academy（中关村学院）；National University of Singapore（新加坡国立大学）；Shanghai Innovation Institute（上海创新研究院）
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University（机械系统与振动国家重点实验室，机械工程学院，上海交通大学）；Shanghai Key Laboratory of Intelligent Robotics, Meta Robotics Institute, Shanghai Jiao Tong University, Shanghai 200240, China（智能机器人上海市重点实验室，元机器人研究院，上海交通大学，上海200240，中国）；The University of Tokyo（东京大学）
FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulation
Department of Computer Science and Engineering, Texas A&M University（德克萨斯A&M大学计算机科学与工程系）；Department of Electrical & Computer Engineering, University of Washington（华盛顿大学电气与计算机工程系）；Karlsruhe Institute of Technology, Germany（德国卡尔斯鲁厄理工学院）
Human-assisted Robotic Policy Refinement via Action Preference Optimization
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing（中国人民大学北京校区人工智能学院）；Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索与推荐工程研究中心）；Beijing Key Laboratory of Research on Large Models（北京大型模型研究重点实验室）
Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning
Stanford University（斯坦福大学）；Technical University of Munich（慕尼黑技术大学）；University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（人工智能研究院）
Trust-Calibrated VLA Policy Post-Training with Evolving Imagination
Sun Yat-sen University（中山大学）；Shenzhen Loop Area Institute（深圳河套学院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shanghai AI Laboratory（上海人工智能实验室）；University of Oxford（牛津大学）；University of Science and Technology of China（中国科学技术大学）
MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
Westlake University（西湖大学）；Zhejiang University（浙江大学）；East China University of Science and Technology（华东理工大学）；Huawei Celia Team（华为Celia团队）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；OpenHelix Robotics
World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；State Key Laboratory of Mobile Network and Mobile Multimedia Technology, ZTE, China（中兴通讯移动网络和移动多媒体技术国家重点实验室）；Sun Yat-sen University（中山大学）
Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
School of Information Science and Technology, Beijing University of Technology（信息科学与技术学院，北京理工大学）；LiAuto Inc.（LiAuto公司）；Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology（计算智能与智能系统北京市重点实验室，北京理工大学）
TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation
Meituan（美团）；Beijing Institute of Technology（北京理工大学）；Beihang University（北京航空航天大学）；State Key Lab of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；China University of Mining and Technology (Beijing)（中国矿业大学（北京））
eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token Routing
Southern University of Science and Technology（南方科技大学）；Beijing Zhongguancun Academy（北京中关村学院）；Samsung Robotics eXperience（三星机器人体验中心）；Wuhan University（武汉大学）；Sun Yat-sen University（中山大学）
RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
Sun Yat-sen University（中山大学）；South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Huawei Noah’s Ark Lab（华为诺亚实验室）
CrossTracer: Cross-Embodiment Navigation via VLA Model Reasoning and Trace Residuals Adapting
Peng Cheng Laboratory（鹏城实验室）；Southern University of Science and Technology（南方科技大学）；Innovation Investment Research Institute（创新投资研究院）；Soochow University（苏州大学）
StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement
GigaAI Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所GigaAI研究院）；Beijing Institute of Technology（北京理工大学）；GigaAI（极佳科技）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
RoboGene: Diversity-Driven Agentic Task Generation Framework for VLA Pre-training
Beijing Innovation Center of Humanoid Robotics（北京人形机器人创新中心）；The School of Advanced Manufacturing and Robotics, Peking University（北京大学先进制造与机器人学院）；Beijing Institute of Technology（北京理工大学）；The School of Mechanical Engineering and Automation, Beihang University（北航机械工程与自动化学院）；State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（北京大学多媒体信息处理国家重点实验室）
AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）；State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（清华大学智能绿色车辆与交通国家重点实验室）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Meituan Inc.（美团公司）；Dongfeng Motor Corporation（东风汽车公司）
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
MoE key Lab of Artificial Intelligence, AI Institute, SJTU（人工智能联合实验室、人工智能研究院、上海交通大学）；HKU MMLab（香港大学多模态实验室）；Shanghai AI Lab（上海人工智能实验室）；D-Robotics（D-机器人）；SZU（深圳大学）；THU（清华大学）；TeleAI；FDU（福建大学）；USTC（中国科学技术大学）；SUSTech（南方科技大学）；SYSU（深圳大学）；CSU（中国科学技术大学）；NEU（南京大学）；HKU-SH ICRC（香港大学深圳研究院）；NJU（南京大学）；Lumina EAI
