2 papers
cs.CL2025
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
Felipe Nuti, Tim Franzmeyer, João Henriques
Past work has studied the effects of fine-tuning on large language models' (LLMs) overall performance on certain tasks. However, a quantitative and systematic method for analyzing…
cs.LG2023
Extracting Reward Functions from Diffusion Models
Felipe Nuti, Tim Franzmeyer, João F. Henriques
Diffusion models have achieved remarkable results in image generation, and have similarly been used to learn high-performing policies in sequential decision-making tasks. Decision-…