Lijun Wu

Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs

Revisiting Long-context Modeling from Context Denoising Perspective

IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment

DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Data Selection

Data-efficient Online Training for Direct Alignment in LLMs

Sequential Diffusion Language Models

ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning

Fast and Accurate Blind Flexible Docking

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic Selection

3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling

Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates

Multi-Agent Collaborative Data Selection for Efficient Language Model Pretraining

SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning