Lu Chen

Decomposing Scientific Paper Queries with Draft-and-Follow Policy Optimization to Narrow Knowing-Doing Gap

DiSRouter: Distributed Self-Routing for LLM Selections

AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation

ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge

Empowering LLM Tool Invocation with Tool-call Reward Model

MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation

Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations

Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling

Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking

Reducing Tool Hallucination via Reliability Alignment

Boosting Long-Context LLM Inference Efficiency with Intra-Layer Attention Similarity