Huanjin Yao

Tiny-R1V: Lightweight Multimodal Unified Reasoning Model via Model Merging

MAPO: MIXED ADVANTAGE POLICY OPTIMIZATION

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation

R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO