paper-with-me

홈 › Papers

Conditional Energy-Based Models for Implicit Policies: The Gap between Theory and Practice

2022-07-12 · Duy-Nguyen Ta, Eric Cousineau, Huihua Zhao, Siyuan Feng

We present our findings in the gap between theory and practice of using conditional energy-based models (EBM) as an implicit representation for behavior-cloned policies. We also clarify several subtle, and potentially confusing, details in previous work in an attempt to help future research in this area. We point out key differences between unconditional and conditional EBMs, and warn that blindly applying training methods for one to the other could lead to undesirable results that do not generalize well. Finally, we emphasize the importance of the Maximum Mutual Information principle as a necessary condition to achieve good generalization in conditional EBMs as implicit models for regression tasks.

📄 PDF Abstract BibTeX arXiv:2207.05824

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

2025-10-02 · Runqian Wang, Yilun Du arxiv

We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based…

Image Denoising

Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation

2026-02-05 · Igor Santos-Grueiro arxiv

Behavioral evaluation is the dominant paradigm for assessing alignment in large language models (LLMs). In current practice, observed compliance under finite evaluation protocols is treated as evidence of latent alignmen…

M-EBM: Towards Understanding the Manifolds of Energy-Based Models

2023-03-08 · Xiulong Yang, Shihao Ji

Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expe…

Image Generation

ConSolv: Solvent-Conditional Machine Learning Implicit Solvent Potential

2026-06-23 · Linying Zhang, Julija Zavadlav arxiv

Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulations. However, existing models have largely focused on aqueous environmen…

Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling

2024-07-21 · Junn Yong Loo, Michelle Adeline, Arghya Pal, Vishnu Monn Baskaran 외

Energy based models (EBMs) are appealing for their generality and simplicity in data likelihood modeling, but have conventionally been difficult to train due to the unstable and time-consuming implicit MCMC sampling duri…

Image GenerationUnconditional Image Generation