3 papers
cs.LG2026
Skill Neologisms: Towards Skill-based Continual Learning
Antonin Berthon, Nicolas Astorga, Mihaela van der Schaar
Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable ma…
cs.CL2026
Language Bottleneck Models for Qualitative Knowledge State Modeling
Antonin Berthon, Mihaela van der Schaar
Accurately assessing student knowledge is central to education. Cognitive Diagnosis (CD) models estimate student proficiency at a fixed point in time, while Knowledge Tracing (KT)…
cs.LG2025
G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration
Samuel Holt, Max Ruiz Luyten, Antonin Berthon +1
Constructing robust simulators is essential for asking "what if?" questions and guiding policy in critical domains like healthcare and logistics. However, existing methods often st…