paper-with-me

홈 › Papers

Relation-R1: Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relational Comprehension

2025-04-20 · Lin Li, Wei Chen, Jiahui Li, Long Chen

Recent advances in multi-modal large language models (MLLMs) have significantly improved object-level grounding and region captioning, but remain limited in visual relation understanding (\eg, scene graph generation), particularly in modeling \textit{N}-ary relationships that identify multiple semantic roles among an action event. Such a lack of \textit{semantic dependencies} modeling among multi-entities leads to unreliable outputs, intensifying MLLMs' hallucinations and over-reliance on language priors. To this end, we propose Relation-R1, the first unified relational comprehension framework that explicitly integrates cognitive chain-of-thought (CoT)-guided Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) within a reinforcement learning (RL) paradigm. Specifically, we first establish foundational reasoning capabilities via SFT, enforcing structured outputs with thinking processes. Then, GRPO is utilized to refine these outputs via multi-reward optimization, prioritizing visual-semantic grounding over language-induced biases, thereby improving generalization capability. Extensive experiments on widely-used PSG and SWiG datasets demonstrate that Relation-R1 achieves state-of-the-art performance in both binary and \textit{N}-ary relation understanding.

📄 PDF Abstract BibTeX arXiv:2504.14642

Code (0)

등록된 구현이 없습니다.

Tasks

Graph GenerationReinforcement Learning (RL)RelationScene Graph Generation

Methods 이 논문이 사용한 방법론

SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…

Similar Papers 제목 키워드 기반

PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought

2026-06-23 · Ling Li, Bowen Liu, Zinuo Zhan, Jianhui Zhong 외 arxiv

Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures. Traditional methods typically encode input i…

Reinforcement LearningVisual Grounding

Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement

2025-03-09 · Yuqi Liu, Bohao Peng, Zhisheng Zhong, Zihao Yue 외

Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes. To addres…

Domain GeneralizationObject DetectionOpen Vocabulary Object DetectionOpen Vocabulary Semantic Segmentation+5

History-Aware Cross-Attention Reinforcement: Self-Supervised Multi Turn and Chain-of-Thought Fine-Tuning with vLLM

2025-06-08 · Andrew Kiruluta, Andreas Lemos, Priscilla Burity

We present CAGSR-vLLM-MTC, an extension of our Self-Supervised Cross-Attention-Guided Reinforcement (CAGSR) framework, now implemented on the high-performance vLLM runtime, to address both multi-turn dialogue and chain-o…

Knowledge Distillation for Large Language Models

2026-03-14 · Alejandro Paredes La Torre, Barbara Flores, Diego Rodriguez arxiv

We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as …

Knowledge DistillationReinforcement Learning

Increasing cognitive-emotional flexibility with meditation and hypnosis: The cognitive neuroscience of de-automatization

2016-05-11

Meditation and hypnosis both aim to facilitate cognitive-emotional flexibility, i.e., the "de-automatization" of thought and behavior. However, little research or theory has addressed how internal thought patterns might …