6 papers
Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation
Aniketh Iyengar, Jiaqi Han, Boris Ruf +3
The rapidly growing computational demands of diffusion models for image generation have raised significant concerns about energy consumption and environmental impact. While existin…
From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes
Rubén Garzón, Pauline Baron, Vincent Grari +3
Large language models (LLM) agents may offer tools to predict human responses to surveys. A common technique for defining these agents uses only demographics, for example country,…
ACT: Agentic Classification Tree
Vincent Grari, Tim Arni, Thibault Laugel +3
When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable and auditable, a requirement increasingly expected by regulation…
Agentic Adversarial QA for Improving Domain-Specific LLMs
Vincent Grari, Ciprian Tomoiaga, Sylvain Lamprier +2
Large Language Models (LLMs), despite extensive pretraining on broad internet corpora, often struggle to adapt effectively to specialized domains. There is growing interest in fine…
SAKE: Steering Activations for Knowledge Editing
Marco Scialanga, Thibault Laugel, Vincent Grari +1
As Large Langue Models have been shown to memorize real-world facts, the need to update this knowledge in a controlled and efficient manner arises. Designed with these constraints…
Controlled Model Debiasing through Minimal and Interpretable Updates
Federico Di Gennaro, Thibault Laugel, Vincent Grari +1
Traditional approaches to learning fair machine learning models often require rebuilding models from scratch, typically without considering potentially existing models. In a contex…