Linjun Zhang

Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards

Secret-Protected Evolution for Differentially Private Synthetic Text Generation

MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning

Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

UQ: Assessing Language Models on Unsolved Questions

Residual Feature Integration is Sufficient to Prevent Negative Transfer

Equitable Elicitation

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

Neat: Nonlinear Parameter-efficient Adaptation of Pre-trained Models

MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment

FactTest: Factuality Testing in Large Language Models with Statistical Guarantees

It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF