Related papers: ProcVLM: Learning Procedure-Grounded Progress Rewa…

Process Reward Models (PRMs) are crucial for guiding Large Language Models (LLMs) in complex scenarios by providing dense reward signals. However, existing PRMs primarily rely on heuristic approaches, which struggle with cross-domain…

Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional rule-based methods fail to scale or generalize in unstructured, novel environments. In recent…

Robot navigation is a crucial task with applications to social robots in dynamic human environments. While Reinforcement Learning (RL) has shown great promise for this problem, the policy quality is highly sensitive to the specification of…

Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning capabilities of large language models (LLMs) by guiding their step-by-step reasoning toward a final answer. However, existing PRMs either treat each…

Diffusion policy has demonstrated promising performance in the field of robotic manipulation. However, its effectiveness has been primarily limited in short-horizon tasks, and its performance significantly degrades in the presence of image…

Large language models (LLMs) have shown promise in robotic procedural planning, yet their human-centric reasoning often omits the low-level, grounded details needed for robotic execution. Vision-language models (VLMs) offer a path toward…

Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations, and therefore requires costly multi-modal data. To compensate for the deficiency of robot data,…

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…

Crop monitoring is essential for precision agriculture, but current systems lack high-level reasoning. We introduce a novel, modular framework that uses a Visual Language Model (VLM) to guide robotic task planning, interleaving input…

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations--cases where…

Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement…

Dexterous robotic hands are essential for performing complex manipulation tasks, yet remain difficult to train due to the challenges of demonstration collection and high-dimensional control. While reinforcement learning (RL) can alleviate…

Prompt learning has been designed as an alternative to fine-tuning for adapting Vision-language (V-L) models to the downstream tasks. Previous works mainly focus on text prompt while visual prompt works are limited for V-L models. The…

Reinforcement learning (RL) requires either manually specifying a reward function, which is often infeasible, or learning a reward model from a large amount of human feedback, which is often very expensive. We study a more sample-efficient…

Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches…

Large Language Models (LLMs) have gained popularity in task planning for long-horizon manipulation tasks. To enhance the validity of LLM-generated plans, visual demonstrations and online videos have been widely employed to guide the…

Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments. However, existing robotic memory benchmarks still lack…

Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users…

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

Many Vision-Language-Action (VLA) models are built upon an internal world model trained via next-frame prediction ``$v_t \rightarrow v_{t+1}$''. However, this paradigm attempts to predict the future frame's appearance directly, without…