Related papers: MVR: Multi-view Video Reward Shaping for Reinforce…

Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising solution…

Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However,…

Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and…

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs) by optimizing them against factual outcomes. However, this paradigm falters in long-context…

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framework, LRS involves…

Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in multiple domains, yet outcome-only scalar rewards are often sparse and uninformative, especially on failed samples, where they merely indicate…

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

Reinforcement learning from verifiable rewards (RLVR) has recently been extended from text-only LLMs to vision-language models (VLMs) to elicit long-chain multimodal reasoning. However, RLVR-trained VLMs still exhibit two persistent failure…

Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated strong semantic understanding capabilities, but struggles to perform precise spatio-temporal understanding. Existing spatio-temporal methods primarily focus on the…

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models…

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,…

Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution…

Vision-language models (VLMs) have shown remarkable abilities by integrating large language models with visual inputs. However, they often fail to utilize visual evidence adequately, either depending on linguistic priors in vision-centric…

Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…

Recent advances in Multimodal Large Language Models (MLLMs) have enabled automated generation of structured layouts from natural language descriptions. Existing methods typically follow a code-only paradigm that generates code to represent…

Vision-language models (VLMs) have achieved impressive results on single-view vision tasks, but lack the multi-view spatial reasoning capabilities essential for embodied AI systems to understand 3D environments and manipulate objects across…

The rapid advancement of Multimodal Large Language Models (MLLMs) has made aligning them with human preferences a critical challenge. Reward Models (RMs) are a core technology for achieving this goal, but a systematic guide for building…

In reinforcement learning (RL), value-based algorithms learn to associate each observation with the states and rewards that are likely to be reached from it. We observe that many self-supervised image pre-training methods bear similarity to…

Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). However, existing datasets are predominantly derived from either…

Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) face two critical challenges: the lack of cross-image reasoning…