David A. Clifton

CE-SSL: Computation-Efficient Semi-Supervised Learning for ECG-based Cardiovascular Diseases Detection

LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models

Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation

Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs

Optimization Inspired Few-Shot Adaptation for Large Language Models

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

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference

Dataset Condensation with Sharpness-Aware Trajectory Matching

Large Learning Rates without the Agonizing Pain: Dispelling the Curse of Singularities in Deep Neural Networks

Efficiently pre-training language models with mixtures of cluster-oriented, trainability-aware experts