V
VisionReasoner
JIA-Lab-research/VisionReasoner
[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
★350stars
Python
Apache-2.0
Updated: 3d ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Models project, built with Python, focusing on counting-objects and multimodal
Who made it?Maintained by JIA-Lab-research team, 350⭐ on GitHub, #2040 out of 3201 in Models
Why does it exist?In the Models space, counting-objects workflows faced efficiency bottlenecks. VisionReasoner was built by JIA-Lab-research to address these multimodal challenges.
What can it do?Key use cases: multimodal-large-language-models, object-detection, reasoning-language-models
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/JIA-Lab-research/VisionReasoner
🔗 github.com/JIA-Lab-research/VisionReasoner
Topics
counting-objectsmultimodalmultimodal-large-language-modelsobject-detectionreasoning-language-modelsreinforcement-learningsegmentationvisual-perception