相关论文: From Goal-Conditioned to Language-Conditioned Agen…

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…

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…

Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when…

We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as…

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose…

Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn actions. Large language models (LLMs) can infer such constraints but are unreliable over long…

Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs often suffer from limitations, such as the high resource…

Vision Language Models exhibit impressive performance for various tasks, yet they often lack the sophisticated situational reasoning required for complex decision-making. This paper shows that VLMs can achieve surprisingly strong…

Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios. Compared to the standard RL solutions that learn a policy solely depending on…

The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs…

Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLMs). Existing VLAs rely on end-to-end supervision to implicitly enable the action decoding process…

We study the problem of learning a range of vision-based manipulation tasks from a large offline dataset of robot interaction. In order to accomplish this, humans need easy and effective ways of specifying tasks to the robot. Goal images…

Recent studies on Vision-Language-Action (VLA) models have shifted from the end-to-end action-generation paradigm toward a pipeline involving task planning followed by action generation, demonstrating improved performance on various…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…

Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…

Integrating visual-language instructions into visuomotor policies is gaining momentum in robot learning for enhancing open-world generalization. Despite promising advances, existing approaches face two challenges: limited language…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physical environment, which…