Diffusion and flow policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions, especially in the context of vision language action (VLA) models. However, high quality policy performance also requires fast inference and high quality demonstrations, which are often hard to get. Lack of these leads to suboptimal policy behaviors and failure under distribution shifts. In this work we address the problem of fine-tuning and accelerating suboptimal flow-based policies using the robot's experience through RL post-training. We introduce Optimal Transport Q-Learning (OTQL), a new method for finetuning flow policies using advantage weighted conditional optimal transport flow matching. OTQL can finetune and accelerate flows with an interaction budget of 50-60 episodes while avoiding computationally expensive distillation in simulation and real-world robot tasks. Our results show that OTQL post-trains flow policies using the robot's own experience, increasing average success percentage of single-task policies from 36% to 86% and of a pre-trained VLA from 38% to 76% while reducing the number of inference steps per action generation by 70%.
Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion
Collaborative and Versatile Robots (CLOVER) Laboratory, T-Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong（协作与多功能机器人实验室，T-Stone机器人研究所，香港中文大学，香港）；Φ \Phi -Institute for Physical Human Intelligence（物理人机智能研究所）；Center for Embodied Artificial Intelligence and Computer Vision, Shenzhen Loop Area Institute, Shenzhen, China（具身人工智能与计算机视觉中心，深圳环园研究院，深圳，中国）；Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy（先进机器人系，意大利理工学院，热那亚，意大利）
TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models
ByteDance Seed（字节跳动种子）；The University of Adelaide（阿德莱德大学）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；The University of Hong Kong（香港大学）；CSIRO Data61
School of Computing and Data Science, The University of Hong Kong（香港大学计算与数据科学学院）；Shanghai Qizhi Institute（上海启智研究院）；Shanghai Jiao Tong University（上海交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）
What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior
University of Technology Nuremberg（纽伦堡工业大学）；ETH Zürich（苏黎世联邦理工学院）；Inria, Ecole Normale Supérieure, CNRS, PSL Research University（法国国家信息与自动化研究所，巴黎高等师范学校，法国国家科学研究中心，巴黎文理研究大学）
Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles
Moscow Institute of Physics and Technology（莫斯科物理技术学院）；JSC Integrant（JSC Integrant公司）；Federal Research Center for Computer Science and Control RAS（俄罗斯科学院计算机科学与控制联邦研究中心）；AIRI
TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance
Shanghai Jiao Tong University（上海交通大学）；Xense Robotics（Xense机器人公司）；Sun Yat-sen University（中山大学）；Oxford（牛津大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；UCSD（加州大学圣地亚哥分校）
Multi-Modal Decentralized Reinforcement Learning for Modular Reconfigurable Lunar Robots
Space Robotics Lab. (SRL) in Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University（太空机器人实验室（SRL）位于东东北大学航空航天工程系研究生院）；Politecnico di Milano（米兰理工大学）
EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment
Department of Automation, Tsinghua University（清华大学自动化系）；Beijing Key Laboratory of Embodied Intelligence Systems（北京具身智能系统重点实验室）；Institute for Embodied Intelligence and Robotics, Tsinghua University（清华大学具身智能与机器人研究所）
VLS: Steering Pretrained Robot Policies via Vision-Language Models
University of Washington（华盛顿大学）；University of Oxford（牛津大学）；National University of Singapore（新加坡国立大学）；Allen Institute for Artificial Intelligence（人工智能研究院）
