Publications

2026

1. NeurIPS Workshop

   LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators

   Riccardo De Santi*, Federico Di Gennaro*, Angelo Gnazzo*, and 6 more authors

   2026

   Agentic AI for Biological Discovery Workshop at NeurIPS 2026

   Bibtex PDF Code Website

   @misc{desanti2026llmtoflowdistillationteachingnatural,
     title = {LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators},
     author = {De Santi*, Riccardo and Di Gennaro*, Federico and Gnazzo*, Angelo and Tang, Sophia and Chatterjee, Pranam and Yang, Fanny and Ceylan, İsmail İlkan and Bronstein, Michael M. and Krause, Andreas},
     year = {2026},
     eprint = {2610.17246},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2610.17246},
     workshop = {Agentic AI for Biological Discovery Workshop at NeurIPS 2026},
   }

2. NeurIPS

   On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

   Trevor Chen, Ariel Dai, Jason Yang, and 8 more authors

   Advances in Neural Information Processing Systems (NeurIPS), 2026

   Bibtex PDF

   @article{chen2026design,
     title = {On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization},
     author = {Chen, Trevor and Dai, Ariel and Yang, Jason and De Santi, Riccardo and Khalil, Daniel and Chu, Wenda and Gruver, Nate and Murugan, Pranav and Goldberg, Alexander F. G. and Al-Shedivat, Maruan and Yue, Yisong},
     journal = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2026},
   }

3. NeurIPS

   Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules

   Riccardo De Santi, Bruce Lee, Cristian Perez Jensen, and 6 more authors

   Advances in Neural Information Processing Systems (NeurIPS), 2026

   Bibtex PDF Code Website

   @article{desanti2026active,
     title = {Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules},
     author = {De Santi, Riccardo and Lee, Bruce and Perez Jensen, Cristian and Protopapas, Kimon and Tang, Sophia and Cheng-Hao, Liu and Chatterjee, Pranam and Yue, Yisong and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2026},
   }

4. ICMLOral Presentation

   A Unified Density Operator View of Flow Control and Merging

   Riccardo De Santi, Malte Franke, Ya-Ping Hsieh, and 1 more author

   International Conference on Machine Learning (ICML), 2026

   Oral at Real-World Constrained and Preference-Aligned Flow and Diffusion-Based Models Workshop at ICLR 2026

   Bibtex PDF

   @article{de2026unified,
     title = {A Unified Density Operator View of Flow Control and Merging},
     author = {De Santi, Riccardo and Franke, Malte and Hsieh, Ya-Ping and Krause, Andreas},
     journal = {International Conference on Machine Learning (ICML)},
     year = {2026},
     award = {Oral at Real-World Constrained and Preference-Aligned Flow and Diffusion-Based Models Workshop at ICLR 2026},
     badge_extra = {Oral Presentation}
   }

5. ICMLOral Presentation

   Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design

   Sven Gutjahr*, Riccardo De Santi*, Luca Schaufelberger*, and 2 more authors

   International Conference on Machine Learning (ICML), 2026

   Oral at Frontiers in Probabilistic Inference Workshop at NeurIPS 2025

   Bibtex PDF Code

   @article{gutjahr2025constrained,
     title = {Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design},
     author = {Gutjahr*, Sven and De Santi*, Riccardo and Schaufelberger*, Luca and Jorner, Kjell and Krause, Andreas},
     journal = {International Conference on Machine Learning (ICML)},
     year = {2026},
     award = {Oral at Frontiers in Probabilistic Inference Workshop at NeurIPS 2025},
     badge_extra = {Oral Presentation}
   }

6. ICML

   Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning

   Zifan Wang, Riccardo De Santi, Xiaoyu Mo, and 3 more authors

   International Conference on Machine Learning (ICML), 2026

   Bibtex PDF

   @article{wang2026efficient,
     title = {Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning},
     author = {Wang, Zifan and De Santi, Riccardo and Mo, Xiaoyu and Zavlanos, Michael M. and Krause, Andreas and Johansson, Karl H.},
     journal = {International Conference on Machine Learning (ICML)},
     year = {2026},
   }

7. ICLR

   Verifier-Constrained Flow Expansion for Discovery Beyond the Data

   Riccardo De Santi*, Kimon Protopapas*, Ya-Ping Hsieh, and 1 more author

   International Conference on Learning Representations (ICLR), 2026

   Bibtex PDF Code

   @article{de2026verifier,
     title = {Verifier-Constrained Flow Expansion for Discovery Beyond the Data},
     author = {De Santi*, Riccardo and Protopapas*, Kimon and Hsieh, Ya-Ping and and Krause, Andreas},
     journal = {International Conference on Learning Representations (ICLR)},
     year = {2026},
   }

8. ICLR

   Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation

   Cristian Perez Jensen, Luca Schaufelberger*, Riccardo De Santi*, and 2 more authors

   International Conference on Learning Representations (ICLR), 2026

   Bibtex PDF

   @article{jensen2025value,
     title = {Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation},
     author = {Jensen, Cristian Perez and Schaufelberger*, Luca and De Santi*, Riccardo and Jorner, Kjell and Krause, Andreas},
     journal = {International Conference on Learning Representations (ICLR)},
     year = {2026},
   }

9. ICLR

   Landing with the Score: Riemannian Optimization through Denoising

   Andrey Kharitenko, Zebang Shen, Riccardo De Santi, and 2 more authors

   International Conference on Learning Representations (ICLR), 2026

   Bibtex PDF

   @article{kharitenko2025landing,
     title = {Landing with the Score: Riemannian Optimization through Denoising},
     author = {Kharitenko, Andrey and Shen, Zebang and De Santi, Riccardo and He, Niao and Doerfler, Florian},
     journal = {International Conference on Learning Representations (ICLR)},
     year = {2026},
   }

2025

1. NeurIPSSpotlight and Oral Presentation

   Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

   Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh, and 3 more authors

   Advances in Neural Information Processing Systems (NeurIPS), 2025

   Spotlight at NeurIPS 2025 and Oral at Workshop on Generative AI and Biology at ICML 2025

   Bibtex PDF Code Website

   @article{de2025flow,
     title = {Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning},
     author = {De Santi, Riccardo and Vlastelica, Marin and Hsieh, Ya-Ping and Shen, Zebang and He, Niao and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2025},
     award = {Spotlight at NeurIPS 2025 and Oral at Workshop on Generative AI and Biology at ICML 2025},
     badge_extra = {Spotlight and Oral Presentation},
   }

2. ICML Workshop

   Efficient Generative Models Personalization via Optimal Experimental Design

   Guy Schacht, Mojmir Mutny, Riccardo De Santi, and 2 more authors

   Workshop on Models of Human Feedback for AI Alignment at ICML, 2025

   Bibtex PDF

   @article{schachtefficient,
     title = {Efficient Generative Models Personalization via Optimal Experimental Design},
     author = {Schacht, Guy and Mutny, Mojmir and De Santi, Riccardo and Sheebaelhamd, Ziyad and Krause, Andreas},
     journal = {Workshop on Models of Human Feedback for AI Alignment at ICML},
     year = {2025},
   }

3. ICML

   Provable Maximum Entropy Manifold Exploration via Diffusion Models

   Riccardo De Santi*, Marin Vlastelica*, Ya-Ping Hsieh, and 3 more authors

   International Conference on Machine Learning (ICML), 2025

   Bibtex PDF Code

   @article{de2025provable,
     title = {Provable Maximum Entropy Manifold Exploration via Diffusion Models},
     author = {De Santi*, Riccardo and Vlastelica*, Marin and Hsieh, Ya-Ping and Shen, Zebang and He, Niao and Krause, Andreas},
     journal = {International Conference on Machine Learning (ICML)},
     year = {2025},
   }

2024

1. ICML

   Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods

   Riccardo De Santi*, Manish Prajapat*, and Andreas Krause

   International Conference on Machine Learning (ICML), 2024

   Bibtex PDF

   @article{de2024global,
     title = {Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods},
     author = {De Santi*, Riccardo and Prajapat*, Manish and Krause, Andreas},
     journal = {International Conference on Machine Learning (ICML)},
     year = {2024},
   }

2. ICML

   Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction

   Riccardo De Santi, Federico Arangath Joseph, Noah Liniger, and 2 more authors

   International Conference on Machine Learning (ICML), 2024

   Bibtex PDF

   @article{de2024geometric,
     title = {Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction},
     author = {De Santi, Riccardo and Arangath Joseph, Federico and Liniger, Noah and Mutti, Mirco and Krause, Andreas},
     journal = {International Conference on Machine Learning (ICML)},
     year = {2024},
   }

3. ICLR

   Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning

   Mirco Mutti, Riccardo De Santi, Marcello Restelli, and 2 more authors

   International Conference on Learning Representations (ICLR), 2024

   Causal Representation Learning Workshop at NeurIPS 2023

   Bibtex PDF

   @article{mutti2023exploiting,
     title = {Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning},
     author = {Mutti, Mirco and De Santi, Riccardo and Restelli, Marcello and Marx, Alexander and Ramponi, Giorgia},
     journal = {International Conference on Learning Representations (ICLR)},
     year = {2024},
     workshop = {Causal Representation Learning Workshop at NeurIPS 2023},
   }

2023

1. JMLR

   Convex Reinforcement Learning in Finite Trials

   Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, and 1 more author

   Journal of Machine Learning Research (JMLR), 2023

   Bibtex PDF

   @article{mutti2023convex,
     title = {Convex Reinforcement Learning in Finite Trials},
     author = {Mutti, Mirco and De Santi, Riccardo and De Bartolomeis, Piersilvio and Restelli, Marcello},
     journal = {Journal of Machine Learning Research (JMLR)},
     year = {2023},
   }

2. AAAI

   Provably efficient causal model-based reinforcement learning for systematic generalization

   Mirco Mutti*, Riccardo De Santi*, Emanuele Rossi, and 3 more authors

   Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023

   Workshop on Spurious Correlations, Invariance, and Stability at ICML 2022 and A Causal View on Dynamical Systems Workshop at NeurIPS 2022

   Bibtex PDF

   @inproceedings{mutti2023provably,
     title = {Provably efficient causal model-based reinforcement learning for systematic generalization},
     author = {Mutti*, Mirco and De Santi*, Riccardo and Rossi, Emanuele and Calderon, Juan Felipe and Bronstein, Michael and Restelli, Marcello},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2023},
     workshop = {Workshop on Spurious Correlations, Invariance, and Stability at ICML 2022 and A Causal View on Dynamical Systems Workshop at NeurIPS 2022},
   }

2022

1. ICML Workshop

   Non-Markovian Policies for Unsupervised Reinforcement Learning in Multiple Environments

   Pietro Maldini*, Mirco Mutti*, Riccardo De Santi, and 1 more author

   2022

   Decision Awareness in Reinforcement Learning Workshop and First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022

   Bibtex PDF

   @inproceedings{maldini2022non,
     title = {Non-Markovian Policies for Unsupervised Reinforcement Learning in Multiple Environments},
     author = {Maldini*, Pietro and Mutti*, Mirco and De Santi, Riccardo and Restelli, Marcello},
     workshop = {Decision Awareness in Reinforcement Learning Workshop and First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022},
     year = {2022},
   }

2. NeurIPS

   Challenging common assumptions in convex reinforcement learning

   Mirco Mutti*, Riccardo De Santi*, Piersilvio De Bartolomeis, and 1 more author

   Advances in Neural Information Processing Systems (NeurIPS), 2022

   Complex Feedback in Online Learning (CFOL) Workshop at ICML 2022

   Bibtex PDF

   @article{mutti2022challenging,
     title = {Challenging common assumptions in convex reinforcement learning},
     author = {Mutti*, Mirco and De Santi*, Riccardo and De Bartolomeis, Piersilvio and Restelli, Marcello},
     journal = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2022},
     workshop = {Complex Feedback in Online Learning (CFOL) Workshop at ICML 2022},
   }

3. ICMLOutstanding Paper

   The Importance of Non-Markovianity in Maximum State Entropy Exploration

   Mirco Mutti*, Riccardo De Santi*, and Marcello Restelli

   International Conference on Machine Learning (ICML), 2022

   Outstanding Paper Award at ICML 2022

   Bibtex Talk PDF

   @inproceedings{mutti2022importance,
     title = {The Importance of Non-Markovianity in Maximum State Entropy Exploration},
     author = {Mutti*, Mirco and De Santi*, Riccardo and Restelli, Marcello},
     booktitle = {International Conference on Machine Learning (ICML)},
     year = {2022},
     award = {Outstanding Paper Award at ICML 2022},
     badge_extra = {Outstanding Paper},
     talk = {https://icml.cc/virtual/2022/oral/16290},
   }