11 citations · 23 across the 14 of their papers we have counts for
11 papers · 1 filter
Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh +3
Adapting large-scale foundation flow and diffusion generative models to optimize task-specific objectives while preserving prior information is crucial for real-world applications…
Optimistic Task Inference for Behavior Foundation Models
Thomas Rupf, Marco Bagatella, Marin Vlastelica +1
Behavior Foundation Models (BFMs) are capable of retrieving high-performing policy for any reward function specified directly at test-time, commonly referred to as zero-shot reinfo…
Epistemically-guided forward-backward exploration
Núria Armengol Urpí, Marin Vlastelica, Georg Martius +1
Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward repres…
Provable Maximum Entropy Manifold Exploration via Diffusion Models
Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh +3
Exploration is critical for solving real-world decision-making problems such as scientific discovery, where the objective is to generate truly novel designs rather than mimic exist…
Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints
Pavel Kolev, Marin Vlastelica, Georg Martius
Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift w…
Causal Action Influence Aware Counterfactual Data Augmentation
Núria Armengol Urpí, Marco Bagatella, Marin Vlastelica +1
Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demons…
Diffusion Generative Inverse Design
Marin Vlastelica, Tatiana López-Guevara, Kelsey Allen +3
Inverse design refers to the problem of optimizing the input of an objective function in order to enact a target outcome. For many real-world engineering problems, the objective fu…
Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning
Marin Vlastelica, Sebastian Blaes, Cristina Pineri +1
We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balan…
Offline Diversity Maximization Under Imitation Constraints
Marin Vlastelica, Jin Cheng, Georg Martius +1
There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these a…
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
Cian Eastwood, Shashank Singh, Andrei Liviu Nicolicioiu +3
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding…
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
Subham Sekhar Sahoo, Anselm Paulus, Marin Vlastelica +3
Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of t…