AI.info
Bei Li
Explore Bei Li on AI.info.
- BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search
- Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
- NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
- MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization