RS
Riccardo De Santi
cs.LGmath.OCcs.ITmath.ITstat.ML
On Valency
published · living versionsW_3qn5hea4·v1 · currentpublished
Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning
with Juan Guevara, Andreas Krause, Raul Astudillo
1 version
Preprints & journals
17 papers in the corpus · 2022–2026LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators2610.17246v1 · Riccardo De Santi, Federico Di Gennaro, Angelo Gnazzo et al.2026 · 0 citationsarXiv
Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules2606.08802v1 · Riccardo De Santi, Bruce Lee, Cristian Perez Jensen et al.2026 · 0 citationsarXiv
Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design2605.30610v1 · Sven Gutjahr, Riccardo De Santi, Luca Schaufelberger et al.2026 · 0 citationsarXiv
Case Study of Bayesian Batch Optimization Strategies for Heterogeneous Catalysts in CO2 Hydrogenation10.26434/chemrxiv.15001703/v3 · Erwin Lam, Kourosh Shariat, Leo Chevalier et al.2026 · 0 citationsChemRxiv
Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning2602.16796v1 · Zifan Wang, Riccardo De Santi, Xiaoyu Mo et al.2026 · 0 citationsarXiv
Verifier-Constrained Flow Expansion for Discovery Beyond the Data2602.15984v1 · Riccardo De Santi, Kimon Protopapas, Ya-Ping Hsieh et al.2026 · 0 citationsarXiv
A Unified Density Operator View of Flow Control and Merging2602.08012v1 · Riccardo De Santi, Malte Franke, Ya-Ping Hsieh et al.2026 · 0 citationsarXiv
Efficient Personalization of Generative Models via Optimal Experimental Design2512.19057v2 · Guy Schacht, Ziyad Sheebaelhamd, Riccardo De Santi et al.2025 · 0 citationsarXiv
Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning2511.22640v1 · Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh et al.2025 · 0 citationsarXiv
Landing with the Score: Riemannian Optimization through Denoising2509.23357v2 · Andrey Kharitenko, Zebang Shen, Riccardo de Santi et al.2025 · 0 citationsarXiv
Provable Maximum Entropy Manifold Exploration via Diffusion Models2506.15385v1 · Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh et al.2025 · 1 citationarXiv
Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction2407.13364v1 · Riccardo De Santi, Federico Arangath Joseph, Noah Liniger et al.2024 · 0 citationsarXiv
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods2407.09905v1 · Riccardo De Santi, Manish Prajapat, Andreas Krause2024 · 0 citationsarXiv
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning2310.07518v2 · Mirco Mutti, Riccardo De Santi, Marcello Restelli et al.2023 · 0 citationsarXiv
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization2202.06545v3 · Mirco Mutti, Riccardo De Santi, Emanuele Rossi et al.2022 · 8 citationsarXiv
The Importance of Non-Markovianity in Maximum State Entropy Exploration2202.03060v2 · Mirco Mutti, Riccardo De Santi, Marcello Restelli2022 · 5 citationsarXiv
Challenging Common Assumptions in Convex Reinforcement Learning2202.01511v3 · Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis et al.2022 · 2 citationsarXiv
Career total: 19 works. 17 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.