Li Du

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning

ACCELERATE SCALING OF LLM FINETUNING VIA QUANTIFYING THE COVERAGE AND DEPTH OF INSTRUCTION SET

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs

UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection