Yasha Wang

ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

GPS: Graph-guided Proactive Information Seeking in Large Language Models

Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL

Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset Distillation

Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation

TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees

DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing

3DS: Decomposed Difficulty Data Selection’s Case Study on LLM Medical Domain Adaptation

LoRA Dropout as a Sparsity Regularizer for Overfitting Reduction