中文
相关论文

相关论文: EXPO-FT: Sample-Efficient Reinforcement Learning F…

200 篇论文

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise…

机器人学 · 计算机科学 2026-05-14 Yuanfang Peng , Jingjing Fu , Chuheng Zhang , Li Zhao , Jiang Bian , Mingyu Liu , Ling Zhang , Jun Zhang , Rui Wang

Vision-Language-Action (VLA) models have shown a strong capability in enabling robots to execute general instructions, yet they struggle with contact-rich manipulation tasks, where success requires precise alignment, stable contact…

机器人学 · 计算机科学 2026-02-16 Yike Zhang , Yaonan Wang , Xinxin Sun , Kaizhen Huang , Zhiyuan Xu , Junjie Ji , Zhengping Che , Jian Tang , Jingtao Sun

Vision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to automate the laborious data collection process in scaling…

Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can…

Vision-Language-Action (VLA) models like OpenVLA demonstrate impressive zero-shot generalization across robotic manipulation tasks but struggle to adapt to specific deployment environments where consistent high performance on a limited set…

机器人学 · 计算机科学 2026-03-09 Shahram Najam Syed , Yatharth Ahuja , Arthur Jakobsson , Jeff Ichnowski

Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in…

机器人学 · 计算机科学 2026-03-24 Zhilong Zhang , Haoxiang Ren , Yihao Sun , Yifei Sheng , Haonan Wang , Haoxin Lin , Zhichao Wu , Pierre-Luc Bacon , Yang Yu

Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit…

机器学习 · 计算机科学 2026-04-16 Angelo Moroncelli , Roberto Zanetti , Marco Maccarini , Loris Roveda

To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to…

机器人学 · 计算机科学 2026-03-04 Shuai Yang , Hao Li , Bin Wang , Yilun Chen , Yang Tian , Tai Wang , Hanqing Wang , Feng Zhao , Yiyi Liao , Jiangmiao Pang

Vision-Language Action (VLA) models significantly advance robotic manipulation by leveraging the strong perception capabilities of pretrained vision-language models (VLMs). By integrating action modules into these pretrained models, VLA…

计算机视觉与模式识别 · 计算机科学 2025-10-20 Shaoqi Dong , Chaoyou Fu , Haihan Gao , Yi-Fan Zhang , Chi Yan , Chu Wu , Xiaoyu Liu , Yunhang Shen , Jing Huo , Deqiang Jiang , Haoyu Cao , Yang Gao , Xing Sun , Ran He , Caifeng Shan

Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and promising potential in solving complex robotic manipulation tasks. However, their substantial parameter sizes and high inference latency pose significant…

机器人学 · 计算机科学 2025-06-24 Yuxuan Chen , Xiao Li

Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn,…

计算机视觉与模式识别 · 计算机科学 2025-11-04 Wenli Xiao , Haotian Lin , Andy Peng , Haoru Xue , Tairan He , Yuqi Xie , Fengyuan Hu , Jimmy Wu , Zhengyi Luo , Linxi "Jim" Fan , Guanya Shi , Yuke Zhu

Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this…

机器人学 · 计算机科学 2026-02-03 Xu Pan , Zhenglin Wan , Xingrui Yu , Xianwei Zheng , Youkai Ke , Ming Sun , Rui Wang , Ziwei Wang , Ivor Tsang

Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup…

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into robotic actions. Despite their recent advancements,…

机器人学 · 计算机科学 2025-05-27 Tuan Van Vo , Tan Quang Nguyen , Khang Minh Nguyen , Duy Ho Minh Nguyen , Minh Nhat Vu

Vision-Language-Action (VLA) models have demonstrated remarkable performance on complex tasks through imitation learning in recent robotic manipulation works. Based on large-scale and high-quality demonstration datasets, existing imitation…

机器人学 · 计算机科学 2026-04-13 Yuquan Xue , Guanxing Lu , Zhenyu Wu , Chuanrui Zhang , Bofang Jia , Zhengyi Gu , Ziwei Wang

Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while failed rollouts are often discarded. We introduce RePO-VLA,…

Vision-language-action (VLA) models demonstrate strong generalization in robotic manipulation but face challenges in complex, real-world tasks. While supervised fine-tuning with demonstrations is constrained by data quality, reinforcement…

机器人学 · 计算机科学 2025-09-18 Piaopiao Jin , Qi Wang , Guokang Sun , Ziwen Cai , Pinjia He , Yangwei You

We introduce RIPT-VLA, a simple and scalable reinforcement-learning-based interactive post-training paradigm that fine-tunes pretrained Vision-Language-Action (VLA) models using only sparse binary success rewards. Existing VLA training…

机器学习 · 计算机科学 2025-05-23 Shuhan Tan , Kairan Dou , Yue Zhao , Philipp Krähenbühl

Vision-Language-Action (VLA) models for autonomous driving often hit a performance plateau during Reinforcement Learning (RL) optimization. This stagnation arises from exploration capabilities constrained by previous Supervised Fine-Tuning…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Yuechen Luo , Qimao Chen , Fang Li , Shaoqing Xu , Jaxin Liu , Ziying Song , Zhi-xin Yang , Fuxi Wen

Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLAC, a general process reward model built upon InternVL and…