Cover Image

Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yan, Li, Long, Xi, Teng, Zeng, Long, Wang, Jingdong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
by: Tan, Huajie, et al.
Published: (2025)

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
by: Xue, Haotian, et al.
Published: (2025)

From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning
by: Wang, Changpeng, et al.
Published: (2025)

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
by: Wu, Junfei, et al.
Published: (2025)

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
by: Lee, Daeun, et al.
Published: (2026)

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
by: Wang, Jiaqi, et al.
Published: (2025)

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
by: Wang, Qiuchen, et al.
Published: (2025)

Training-Free Unsupervised Prompt for Vision-Language Models
by: Long, Sifan, et al.
Published: (2024)

Bad Seeing or Bad Thinking? Rewarding Perception for Vision-Language Reasoning
by: Wang, Haozhe, et al.
Published: (2026)

Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks
by: Zhang, Yunqi, et al.
Published: (2024)

Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
by: Jiang, Yanbei, et al.
Published: (2025)

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning
by: Zhang, Yizhen, et al.
Published: (2025)

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
by: Feng, Sicheng, et al.
Published: (2025)

Reasoning under Vision: Understanding Visual-Spatial Cognition in Vision-Language Models for CAPTCHA
by: Song, Python, et al.
Published: (2025)

Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation
by: Yang, Guangjing, et al.
Published: (2026)

Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities
by: Li, Zhiyuan, et al.
Published: (2024)

Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
by: Bigverdi, Mahtab, et al.
Published: (2024)

Explain Before You Answer: A Survey on Compositional Visual Reasoning
by: Ke, Fucai, et al.
Published: (2025)

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
by: Pan, Jiazhen, et al.
Published: (2025)

CompareBench: A Benchmark for Visual Comparison Reasoning in Vision-Language Models
by: Cai, Jie, et al.
Published: (2025)

VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning
by: Yan, Hao, et al.
Published: (2025)

VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework
by: Wang, Chao, et al.
Published: (2025)

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
by: Zheng, Haojie, et al.
Published: (2024)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
by: Che, Liwei, et al.
Published: (2026)

MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models
by: Wang, Kangkang, et al.
Published: (2026)

ReasonEdit: Editing Vision-Language Models using Human Reasoning
by: Qiu, Jiaxing, et al.
Published: (2026)

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
by: Huang, Chi-Pin, et al.
Published: (2025)

Enhancing Advanced Visual Reasoning Ability of Large Language Models
by: Li, Zhiyuan, et al.
Published: (2024)

The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
by: Liu, Anjie, et al.
Published: (2026)

Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning
by: Zhao, Bingchen, et al.
Published: (2024)

Simple o3: Towards Interleaved Vision-Language Reasoning
by: Wang, Ye, et al.
Published: (2025)

Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
by: Liu, Junming, et al.
Published: (2026)

WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models
by: Du, Wanjun, et al.
Published: (2026)

The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study
by: Zhang, Weichen, et al.
Published: (2025)

A Two-Stage Globally-Diverse Adversarial Attack for Vision-Language Pre-training Models
by: Chen, Wutao, et al.
Published: (2026)

GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation
by: Guo, Shasha, et al.
Published: (2025)

DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
by: Shi, Xinrui, et al.
Published: (2026)

Prompting Large Vision-Language Models for Compositional Reasoning
by: Ossowski, Timothy, et al.
Published: (2024)

Jailbreaks on Vision Language Model via Multimodal Reasoning
by: Noheria, Aarush, et al.
Published: (2026)

Bongards at the Boundary of Perception and Reasoning: Programs or Language?
by: Langenfeld, Cassidy, et al.
Published: (2026)