2 papers
cs.LG2026
Can AI Scientist Agents Learn from Lab-in-the-Loop Feedback? Evidence from Iterative Perturbation Discovery
Gilles Wainrib, Barbara Bodinier, Haitem Dakhli +5
Recent work has questioned whether large language models (LLMs) can perform genuine in-context learning (ICL) for scientific experimental design, with prior studies suggesting that…
cs.LG2025
Predicting gene essentiality and drug response from perturbation screens in preclinical cancer models with LEAP: Layered Ensemble of Autoencoders and Predictors
Barbara Bodinier, Gaetan Dissez, Lucile Ter-Minassian +5
High-throughput preclinical perturbation screens, where the effects of genetic, chemical, or environmental perturbations are systematically tested on disease models, hold significa…