arXiv Machine Learning June 5, 2026 By Zehua Cheng, Wei Dai, Jiahao Sun

Equivariant Neural Belief Propagation

Read the original on arXiv Machine Learning →

arXiv:2606. 06344v1 Announce Type: new Abstract: Probabilistic inference over spatially embedded variables requires beliefs that respect $SE(3)$ symmetry, yet existing equivariant networks produce only scalars and vectors -- not the rank-2 precision tensors needed for anisotropic uncertainty, and single-component messages collapse multi-modal energy landscapes to physically meaningless averages.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 30

Representation Learning for Equivariant Inference with Guarantees

arXiv:2505. 19809v3 Announce Type: replace-cross Abstract: In many real-world applications of regression, conditional probability estimation, and uncertainty quantification, exploiting symmetries rooted in physics or geometry can dramatically improve generalization and sample efficiency.

By Daniel Ordo\~nez-Apraez, Vladimir Kosti\'c, Alek Fr\"ohlich, Vivien Brandt, Karim Lounici, Massimiliano Pontil

robotics

arXiv Machine Learning

Jun 4

In-Context Graphical Inference

arXiv:2606. 05042v1 Announce Type: new Abstract: Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth graphs, while iterative approximations (Belief Propagation, variational methods) sacrifice convergence guarantees on frustrated topologies.

By Zehua Cheng, Wei Dai, Jiahao Sun

llms benchmarks safety

arXiv Machine Learning

Jul 7

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

arXiv:2607. 03809v1 Announce Type: new Abstract: Normalising flows provide a powerful variational family for approximate inference, yet individual architectures often fail to generalise across heterogeneous posterior geometries.

By Benjamin Wiriyapong, Oktay Karakus, Can Eyupoglu, Kirill Sidorov

multimodal benchmarks

arXiv AI

Jun 2

UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures

arXiv:2606. 01443v1 Announce Type: cross Abstract: A central difficulty in training Joint-Embedding Predictive Architectures (JEPAs) is preventing representation collapse.

By Triet M. Le

rag

arXiv Machine Learning

Aug 4

Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

arXiv:2512. 04954v3 Announce Type: replace Abstract: We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling.

By Rajneil Baruah

multimodal benchmarks

arXiv AI

Jun 3

EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs

arXiv:2606. 03260v1 Announce Type: cross Abstract: Deep learning surrogates for 3D Partial Differential Equations (PDEs) often fail to generalize across geometric transformations because they depend heavily on specific coordinate systems.

By Sungwon Kim, Juho Song, Seungmin Shin, Guimok Cho, Sangkook Kim, Chanyoung Park

Related stories

Representation Learning for Equivariant Inference with Guarantees

In-Context Graphical Inference

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures

Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs