GThinker is a strong MLLM skilled in multimodal reasoning across scenarios.
YufeiZhan
JefferyZhan
AI & ML interests
None yet
Organizations
None yet
A collection of LVLMs enhanced by Vision-R1
-
JefferyZhan/Griffon-G-Llama2-7B-Vision-R1
7B • Updated • 1 -
JefferyZhan/Qwen2.5-VL-7B-Instruct-Vision-R1
8B • Updated • 6 • 1 -
JefferyZhan/Vision-R1-Data
Viewer • Updated • 46.1k • 429 • 3 -
Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
Paper • 2503.18013 • Published • 20
GThinker is a strong MLLM skilled in multimodal reasoning across scenarios.
A collection of LVLMs enhanced by Vision-R1
-
JefferyZhan/Griffon-G-Llama2-7B-Vision-R1
7B • Updated • 1 -
JefferyZhan/Qwen2.5-VL-7B-Instruct-Vision-R1
8B • Updated • 6 • 1 -
JefferyZhan/Vision-R1-Data
Viewer • Updated • 46.1k • 429 • 3 -
Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
Paper • 2503.18013 • Published • 20
An LMM bridges the vision-centric and vision-language tasks