Huajun Chen

Scaling Generalist Data-Analytic Agents

LightMem: Lightweight and Efficient Memory-Augmented Generation

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning

Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning

Adaptive Curriculum Learning for RLHF with Influence-Based Cluster Bandits

FaithThinker: Dialectical Reasoning for Noise-Robust LLMs

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning

InnoGym: Benchmarking the Innovation Potential of AI Agents

Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images

Knowledge-enhanced MCTS for LLM-based Medical Diagnosis Reasoning

OceanGym: A Benchmark Environment for Underwater Embodied Agents

Can Large Language Models Think Like Doctors? An Interactive Approach to Evaluating Clinical Reasoning

SRA-SD: A Lightweight Framework for Structure-Guided Compositional Image Synthesis

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts

SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models

Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning

Benchmarking Agentic Workflow Generation

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Exploring Model Kinship for Merging Large Language Models

SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models

Croppable Knowledge Graph Embedding

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks

Symbolic Learning Enables Self-Evolving Agents

scKGOT: Intercellular Signaling Inference with Knowledge Graph Optimal Transport for Single-cell Transcriptomics