134 citations · 330 across the 35 of their papers we have counts for
21 papers · 1 filter
LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators
Riccardo De Santi, Federico Di Gennaro, Angelo Gnazzo +6
Generative discovery in science requires coupling high-level scientific reasoning with the ability to generate samples respecting the structure of a design space. Yet these capabil…
How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?
Julia Kostin, Kasra Jalaldoust, Elias Bareinboim +2
Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on. Recent work in causality-base…
Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity
Zifan Lyu, Chahine Nejma, Tobias Wegel +2
Large Language Models are typically benchmarked by evaluating every model on every test query. For practitioners seeking the best model to deploy, this is often wasteful: if a mode…
Fast Unlearning at Scale via Margin Self-Correction
Federico Di Gennaro, Alexander Shevchenko, Fanny Yang
Language-model unlearning updates a trained model to behave as if it had not seen selected training examples, while preserving utility and avoiding costly retraining. Existing appr…
ROC-n-reroll: How verifier imperfection affects test-time scaling
Florian E. Dorner, Yatong Chen, André F. Cruz +1
Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied techniques such as Best-of-N (Bo…
Strong Copyright Protection for Language Models via Adaptive Model Fusion
Javier Abad, Konstantin Donhauser, Francesco Pinto +1
The risk of language models unintentionally reproducing copyrighted material from their training data has led to the development of various protective measures. In this paper, we p…