Related papers: PDCR: Perception-Decomposed Confidence Reward for …

Vision-Language Models (VLMs) are becoming the cornerstone of high-level reasoning for robotic automation, enabling robots to parse natural language commands and perceive their environments. However, their susceptibility to hallucinations…

Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with…

Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically rely on supervised weight edits or global penalties; reinforcement-learning…

Visual understanding is inherently intention-driven - humans selectively focus on different regions of a scene based on their goals. Recent advances in large multimodal models (LMMs) enable flexible expression of such intentions through…

Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience.…

Automating radiology report generation with Large Vision-Language Models (LVLMs) holds great potential, yet these models often produce clinically critical hallucinations, posing serious risks. Existing hallucination detection methods…

Learning generalizable reward functions is a core challenge in embodied intelligence. Recent work leverages contrastive vision language models (VLMs) to obtain dense, domain-agnostic rewards without human supervision. These methods adapt…

Defining reward functions for skill learning has been a long-standing challenge in robotics. Recently, vision-language models (VLMs) have shown promise in defining reward signals for teaching robots manipulation skills. However, existing…

Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way. In this paper, we address three critical challenges for this task in a reinforcement learning…

Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text descriptions. However, current models, trained to produce…

Reinforcement learning from verifiable rewards (RLVR) stimulates the thinking processes of large language models (LLMs), substantially enhancing their reasoning abilities on verifiable tasks. It is often assumed that similar gains should…

Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world. The VCR task, which calls for exploiting the…

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Mathematical reasoning is a central challenge for large language models (LLMs), requiring not only correct answers but also faithful reasoning processes. Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising…

Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack…

The capabilities of Large Vision-Language Models (LVLMs) have reached state-of-the-art on many visual reasoning tasks, including chart reasoning, yet they still falter on out-of-distribution (OOD) data, and degrade further when asked to…

Test-time scaling has been shown to substantially improve large language models' (LLMs) mathematical reasoning. However, for a large portion of mathematical corpora, especially theorem proving, RLVR's scalability is limited: intermediate…

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image content, leading to reconstructed results that are both…