Related papers: IG-RFT: An Interaction-Guided RL Framework for VLA…

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…

Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-horizon tasks due to distribution shift and error accumulation.…

Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. Despite these…

Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Language-Action (VLA) models to master dexterous manipulation…

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…

Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…

Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world…

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…

Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significantly improved natural language interaction with such…

Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. Recent open-source work like DeepSeek-R1 demonstrates…

We present GR-RL, a robotic learning framework that turns a generalist vision-language-action (VLA) policy into a highly capable specialist for long-horizon dexterous manipulation. Assuming the optimality of human demonstrations is core to…

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…

This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VLA) models for long-horizon navigation. Unlike existing single-turn paradigm, LongNav-R1…

Vision-Language-Action (VLA) models have shown great potential in general robotic decision-making tasks via imitation learning. However, the variable quality of training data often constrains the performance of these models. On the other…

Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences.…

Vision-Language-Action (VLA) models have become a cornerstone in robotic policy learning, leveraging large-scale multimodal data for robust and scalable control. However, existing VLA frameworks primarily address short-horizon tasks, and…

Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action space. However, despite…

Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform…

Teaching robots dexterous skills from human videos remains challenging due to the reliance on low-level trajectory imitation, which fails to generalize across object types, spatial layouts, and manipulator configurations. We propose…

Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action accuracy of these models on complex downstream tasks is unsatisfactory. One…