Wai Lam

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics

InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing

DocReward: A Document Reward Model for Structuring and Stylizing

Probing Confidence Regions for Early Exits in Chain-of-Thought

Improving Multi-step RAG with Hypergraph-based Memory

Harnessing Webpage UIs for Text-Rich Visual Understanding

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models