Jiaxuan You

Self-Aligned Reward: Towards Effective and Efficient Reasoners

Towards Strategic Persuasion with Language Models

GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs

ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind

ResearchArcade: Graph Interface for Academic Tasks

h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network

GMTRouter: Personalized LLM Router over Multi-turn User Interactions

Building Social World Model with Large Language Models

LRanker: LLM Ranker for Massive Candidates

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data

Which LLM Multi-Agent Protocol to Choose?

ArtifactLinker: Linking Scientific Artifacts for Automatic SOTA Discovery

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare

Debugging Tabular Log as Dynamic Graphs

Where LLM Agents Fail And How They can Learn From Failures

UniRec: Unified Multimodal Encoding for LLM-Based Recommendations

Sotopia-RL: Reward Design for Social Intelligence

R1-Ranker: Teaching LLM Rankers to Reason

SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning in Text-Only LLMs

Multi-Agent Evolve: LLM Self-Improve through Multi-Agent Co-evolution

Learning Argumentative Summarization with Iterative Rejection Sampling

Knowledge Debugger: Diagnosis of Knowledge Inconsistency with Multimodal Graph

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation

Graph World Model

GraphRouter: A Graph-based Router for LLM Selections

Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs

Research Town: Simulator of Research Community

Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Models

PREMIUM: LLM Personalization with Individual-level Preference Feedback

ResearchTown: Simulator of Human Research Community

AcademicEval: Live Long-Context LLM Benchmark

Thought-Retriever: Don’t Just Retrieve Raw Data, Retrieve Thoughts

Instruction Following is not all you need: Rethinking LLM Generation's Evaluation