PhD student, Institute of Science and Technology Austria
3 papers at NeurIPS 2025
Influence Distillation is a mathematically justified data selection method for LLM fine-tuning that assigns optimal weights to training samples, achieving performance on par with or better than state-of-the-art while being substantially faster.
We provide a method for accurate end-to-end FP4 training of Large Language Models.
A low-precision scheme for fine-tuning LLMs
