Related papers: ReinboT: Amplifying Robot Visual-Language Manipula…

Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of…

Robot learning from interacting with the physical world is fundamentally bottlenecked by the cost of physical interaction. The two alternatives, supervised finetuning (SFT) from expert demonstrations and reinforcement learning (RL) in a…

Vision-Language-Action (VLA) models have recently emerged as powerful general-purpose policies for robotic manipulation, benefiting from large-scale multi-modal pre-training. However, they often fail to generalize reliably in…

Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…

Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging,…

Large language models (LLMs) and classical machine learning methods offer complementary strengths for predictive modeling, yet their fundamentally different representations and training paradigms hinder effective integration: LLMs rely on…

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…

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…

Scaling vision-language-action (VLA) model pre-training requires large volumes of diverse, high-quality manipulation trajectories. Most current data is obtained via human teleoperation, which is expensive and difficult to scale.…

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…

Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with…

Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance during deployment. However, standard offline Supervised…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning. However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading…

A generalist robot should perform effectively across various environments. However, most existing approaches heavily rely on scaling action-annotated data to enhance their capabilities. Consequently, they are often limited to single…

This work presents reinforcement learning (RL)-driven data augmentation to improve the generalization of vision-action (VA) models for dexterous grasping. While real-to-sim-to-real frameworks, where a few real demonstrations seed…

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…

Robots and autonomous agents often complete goal-based tasks with limited resources, relying on imperfect models and sensor measurements. In particular, reinforcement learning (RL) and feedback control can be used to help a robot achieve a…

Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the…

Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection. They significantly outperform the best fast-thinking models, such as GPT-4o, on…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for robot learning, but their representations are still largely inherited from static image-text pretraining, leaving physical dynamics to be learned from…