Related papers: TOPReward: Token Probabilities as Hidden Zero-Shot…

Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the final outcome is successful. Existing reward models often rely on trajectory-level success…

Teaching robots novel skills with demonstrations via human-in-the-loop data collection techniques like kinesthetic teaching or teleoperation puts a heavy burden on human supervisors. In contrast to this paradigm, it is often significantly…

Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. However, when used as evaluators in reinforcement learning (RL), today's…

Learning reward functions remains the bottleneck to equip a robot with a broad repertoire of skills. Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. However,…

Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…

Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular,…

Vision-Language-Action (VLA) models have demonstrated remarkable generalization capabilities in robotic manipulation tasks, yet their substantial computational overhead remains a critical obstacle to real-world deployment. Improving…

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and…

Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs)…

Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visual inputs. Existing alignment approaches often rely on…

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 process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks. This frame-by-frame processing makes models vulnerable to visual…

Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined…

Vision-language models (VLMs) have demonstrated excellent high-level planning capabilities, enabling locomotion skill learning from video demonstrations without the need for meticulous human-level reward design. However, the improper frame…

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…

Process-supervised reward models serve as a fine-grained function that provides detailed step-wise feedback to model responses, facilitating effective selection of reasoning trajectories for complex tasks. Despite its advantages, evaluation…

Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning…

Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but…

Vision-Language-Action (VLA) models pretrained on large-scale multimodal datasets have emerged as powerful foundations for robotic perception and control. However, their massive scale, often billions of parameters, poses significant…

Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of…