A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models

Implicit generation and generalization methods for energy-based models

We’ve made progress towards stable and scalable training of energy-based models (EBMs) resulting in better sample quality and generalization ability than existing models. Generation in EBMs spends more compute to continually refine its answers and doing so can generate samples competitive with GANs at low temperatures, while also having mode coverage guarantees of likelihood-based models.

Q-based Variational Inverse Reinforcement Learning

arXiv:2608. 16888v1 Announce Type: new Abstract: The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences.

Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm

arXiv:2607. 00926v1 Announce Type: cross Abstract: Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable.

Transfer from simulation to real world through learning deep inverse dynamics model

An invertible generative model for forward and inverse problems

arXiv:2509. 03910v2 Announce Type: replace-cross Abstract: We formulate inverse problems in a Bayesian framework and aim to train an invertible generative model that is capable of simulation (i.

Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models

arXiv:2607. 07763v1 Announce Type: new Abstract: World models are typically trained to predict discrete-time physical dynamics with a fixed step size baked into the model weights, preventing prediction at variable temporal resolutions.

Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems

arXiv:2508. 09156v3 Announce Type: replace-cross Abstract: We present a framework for fine-tuning flow-matching generative models to enforce physical constraints and solve inverse problems in scientific systems.

Neural Langevin Machine: a local asymmetric learning rule can be creative

arXiv:2506. 23546v2 Announce Type: replace-cross Abstract: Fixed points of recurrent neural networks can be leveraged to store and generate information.

Generative Models: Principles, Architectures, and Applications

arXiv:2608. 08101v1 Announce Type: new Abstract: Generative AI has emerged as one of the most transformative forces in modern artificial intelligence, reshaping how we create, imagine, and interact with digital content.

Local Learning Rules for Out-of-Equilibrium Physical Generative Models

arXiv:2506. 19136v4 Announce Type: replace Abstract: We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules.

Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces

arXiv:2603. 14798v2 Announce Type: replace-cross Abstract: We propose a machine-learning algorithm for Bayesian inverse problems in the function-space regime.

Equilibrium Propagation for Non-Conservative Systems

arXiv:2602. 03670v2 Announce Type: replace-cross Abstract: Equilibrium Propagation (EP) is a physics-inspired learning algorithm that uses stationary states of a dynamical system both for inference and learning.