Yongbin Li

Adaptive Social Learning via Mode Policy Optimization for Language Agents

Agentic Reinforcement Learning with Implicit Step Rewards

MuEdit: A Lightweight yet Effective Multi-task Model Editing Method

P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling

A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models

FrontierBench: Are We Only Testing Agents Under the Streetlight?

TimeHC-RL: Temporal‑aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence

On the Role of Attention Heads in Large Language Model Safety

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct

Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement

Locate-then-Unlearn: An Effective Method of Multi-Task Continuous Learning for Large Language Models

ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration

In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?