3 citations · 5 across the 12 of their papers we have counts for
12 papers · 1 filter
On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
Trevor Chen, Ariel Dai, Jason Yang +8
Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures. At test time, however, the goal is not to sample…
Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
Riccardo De Santi, Bruce Lee, Cristian Perez Jensen +6
Standard flow and diffusion pre-training matches the distribution of available data (e.g., molecules), which often covers only a small fraction of the valid design space. In genera…
Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
Zifan Wang, Riccardo De Santi, Xiaoyu Mo +3
Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment. Existing entropy-regularized methods primarily maximize expe…
Verifier-Constrained Flow Expansion for Discovery Beyond the Data
Riccardo De Santi, Kimon Protopapas, Ya-Ping Hsieh +1
Flow and diffusion models are typically pre-trained on limited available data (e.g., molecular samples), covering only a fraction of the valid design space (e.g., the full molecula…
A Unified Density Operator View of Flow Control and Merging
Riccardo De Santi, Malte Franke, Ya-Ping Hsieh +1
Recent progress in large-scale flow and diffusion models raised two fundamental algorithmic challenges: (i) control-based reward adaptation of pre-trained flows, and (ii) integrati…
Efficient Personalization of Generative Models via Optimal Experimental Design
Guy Schacht, Ziyad Sheebaelhamd, Riccardo De Santi +2
Preference learning from human feedback has the ability to align generative models with the needs of end-users. Human feedback is costly and time-consuming to obtain, which creates…
Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity
Riccardo Santi, Riccardo Salami, Simone Calderara
Nowdays, there are an abundance of portable devices capable of collecting large amounts of data and with decent computational power. This opened the possibility to train AI models…
Landing with the Score: Riemannian Optimization through Denoising
Andrey Kharitenko, Zebang Shen, Riccardo de Santi +2
Under the data manifold hypothesis, high-dimensional data are concentrated near a low-dimensional manifold. We study the problem of Riemannian optimization over such manifolds when…
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
Mirco Mutti, Riccardo De Santi, Marcello Restelli +2
Posterior sampling allows exploitation of prior knowledge on the environment's transition dynamics to improve the sample efficiency of reinforcement learning. The prior is typicall…
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization
Mirco Mutti, Riccardo De Santi, Emanuele Rossi +3
In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as…
The Importance of Non-Markovianity in Maximum State Entropy Exploration
Mirco Mutti, Riccardo De Santi, Marcello Restelli
In the maximum state entropy exploration framework, an agent interacts with a reward-free environment to learn a policy that maximizes the entropy of the expected state visitations…
Challenging Common Assumptions in Convex Reinforcement Learning
Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis +1
The classic Reinforcement Learning (RL) formulation concerns the maximization of a scalar reward function. More recently, convex RL has been introduced to extend the RL formulation…