研究室发布ICLR 2026细粒度识别大模型FineR1源代码
Hulingxiao He, Zijun Geng and Yuxin Peng*, "Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning", The Fourteenth International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, Apr. 23-27, 2026. (Accept)【pdf】【source code】【量子位报道】【极市平台报道】【CVer报道】【宣传海报】【Slides】