Search

Ganqu Cui

Free Process Rewards without Process Labels
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond.
Process reinforcement through implicit rewards.
Advancing LLM Reasoning Generalists with Preference Trees
Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention
UltraMedical: Building Specialized Generalists in Biomedicine

Published with Wowchemy — the free, open source website builder that empowers creators.