R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
Paper • 2508.21113 • Published • 111 •
2
YannQi
YannQi
AI & ML interests
Computer vision, AGI, Multi-modality.
Recent Activity
authored a paper about 1 month ago
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild authored a paper about 1 month ago
MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning authored a paper about 1 month ago
CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question AnsweringOrganizations
Issue serving YannQi/R-4B with official vLLM Docker image
2
#3 opened about 1 year ago
by 
vm7608
can you provide onnx model weights?
1
#2 opened about 1 year ago
by 
ningpp
Update pipeline_tag and add library_name for R-4B
#1 opened about 1 year ago
by 
nielsr
commented a
paper about 1 year ago
Release MoonViT Seperately?
3
#3 opened over 1 year ago
by 
Rkyzzy