Jiawei Han

Preference Leakage: A Contamination Problem in LLM-as-a-judge

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

GRACE: Generative Representation Learning via Contrastive Policy Optimization

mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules

Geometric Constraints for Small Language Models to Understand and Expand Scientific Taxonomies

Think Twice: Branch-and-Rethink Reasoning Reward Model

RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation

Vibe Checker: Aligning Code Evaluation with Human Preference

RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation

Hybrid Latent Reasoning via Reinforcement Learning

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts

RAST: Reasoning Activation in LLMs via Small-model Transfer

Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Law of the Weakest Link: Cross Capabilities of Large Language Models

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval

Benchmarking Retrieval-Augmented Generation for Chemistry

Establishing Knowledge Preference in Language Models

Multi-modal Prompt Learning Empowers Graph Neural Networks with Semantic Knowledge

Synergistic Weak-Strong Collaboration by Aligning Preferences

CoDiCast: Conditional Diffusion Model for Weather Prediction with Uncertainty Quantification