Wenji Mao

Adaptive Social Learning via Mode Policy Optimization for Language Agents

From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization

SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start

Scientific logicality enriched methodology for LLM reasoning: A practice in physics

Enhancing Adversarial Robustness of LLMs with Analytic Hierarchy Process