Cover Image

What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xirui, Li, Ming, Zhou, Tianyi
Format:	Preprint
Published:	2026
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

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
by: Zhou, Hengguang, et al.
Published: (2025)

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions
by: Fan, Chenrui, et al.
Published: (2025)

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning
by: Li, Ming, et al.
Published: (2025)

StyleVAR: Controllable Image Style Transfer via Visual Autoregressive Modeling
by: Jing, Liqi, et al.
Published: (2026)

SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
by: Guo, Xiaojun, et al.
Published: (2025)

Vero: An Open RL Recipe for General Visual Reasoning
by: Sarch, Gabriel, et al.
Published: (2026)

Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
by: Yan, Han, et al.
Published: (2024)

Style-Preserving Lip Sync via Audio-Aware Style Reference
by: Zhong, Weizhi, et al.
Published: (2024)

PyVision-RL: Forging Open Agentic Vision Models via RL
by: Zhao, Shitian, et al.
Published: (2026)

Visual Text Compression as Measure Transport
by: Tang, Lv, et al.
Published: (2026)

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

SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL
by: Liu, Lijun, et al.
Published: (2026)

Focus On What Matters: Separated Models For Visual-Based RL Generalization
by: Zhang, Di, et al.
Published: (2024)

Agentic Spatio-Temporal Grounding via Collaborative Reasoning
by: Zhao, Heng, et al.
Published: (2026)

StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
by: Li, Yanjie, et al.
Published: (2025)

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
by: Shi, Fan, et al.
Published: (2025)

Unbiased Visual Reasoning with Controlled Visual Inputs
by: Li, Zhaonan, et al.
Published: (2025)

Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection
by: Li, Wenqiao, et al.
Published: (2025)

Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
by: Li, Zejun, et al.
Published: (2025)

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning
by: Guo, Garvin, et al.
Published: (2026)

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

Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
by: Xu, Haoran, et al.
Published: (2026)

Reasoning Matters for 3D Visual Grounding
by: Huang, Hsiang-Wei, et al.
Published: (2026)

CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models
by: Nguyen, Quang-Binh, et al.
Published: (2025)

BrainDecoder: Style-Based Visual Decoding of EEG Signals
by: Choi, Minsuk, et al.
Published: (2024)

One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training
by: Yu, Jia, et al.
Published: (2025)

AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences
by: Li, Jieyu, et al.
Published: (2025)

Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline
by: Zhou, Hui, et al.
Published: (2025)

Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving
by: Wang, Jian, et al.
Published: (2025)

Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
by: Xue, Qiyao, et al.
Published: (2025)

MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?
by: Li, Xirui, et al.
Published: (2024)

ArchiLense: A Framework for Quantitative Analysis of Architectural Styles Based on Vision Large Language Models
by: Zhong, Jing, et al.
Published: (2025)

Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models
by: Chen, Yan, et al.
Published: (2025)

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
by: Li, Yiwei, et al.
Published: (2026)

Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL
by: Zhong, Fangwei, et al.
Published: (2024)

Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models
by: Zhan, Yufei, et al.
Published: (2025)

StyleRF-VolVis: Style Transfer of Neural Radiance Fields for Expressive Volume Visualization
by: Tang, Kaiyuan, et al.
Published: (2024)

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

Dance Style Recognition Using Laban Movement Analysis
by: Turab, Muhammad, et al.
Published: (2025)

A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
by: Liu, Huijie, et al.
Published: (2025)