arXiv Machine Learning June 4, 2026 By Zehua Cheng, Wei Dai, Jiahao Sun

In-Context Graphical Inference

Read the original on arXiv Machine Learning →

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.

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

arXiv AI

Jun 11

From Uniform to Learned Graph Priors: Diffusion for Structure Discovery

arXiv:2606. 11831v1 Announce Type: cross Abstract: Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges.

By Qi Shao, Hao Guo, Jiawen Chen, Duxin Chen, Wenwu Yu

diffusion benchmarks

arXiv Machine Learning

Jul 10

Learning $\mathsf{AC}^0$ under Locally Sampleable Graphical Models

arXiv:2607. 08303v1 Announce Type: new Abstract: The problem of learning constant-depth circuits holds profound implications for computational learning theory.

By Weiming Feng, Xiongxin Yang, Yixiao Yu, Yiyao Zhang

arXiv Machine Learning

Jun 5

Equivariant Neural Belief Propagation

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.

By Zehua Cheng, Wei Dai, Jiahao Sun

agents diffusion robotics multimodal

arXiv Machine Learning

Jul 7

Statistically Meaningful Geometry (SMG) Beyond the Euclidean Paradigm, with Application to Generative AI

arXiv:2607. 03329v1 Announce Type: new Abstract: Conventional uniform convergence bounds and empirical risk minimization break down in massive over-parameterized models, such as large language transformers and biological sequence networks.

By Bing Cheng, Yi-Shuai Niu, Howell Tong, Shing-Tung Yau

llms fine-tuning safety

arXiv Machine Learning

Jun 19

Prior-Informed Flow Matching for Graph Reconstruction

arXiv:2601. 22107v2 Announce Type: replace Abstract: We introduce \textit{Prior-Informed Flow Matching (PIFM)}, a conditional flow model for graph reconstruction.

By Harvey Chen, Nicolas Zilberstein, Santiago Segarra

rag diffusion benchmarks

arXiv AI

Jul 21

Breaking the Factorization Barrier in Diffusion Language Models

arXiv:2603. 00045v3 Announce Type: replace-cross Abstract: Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously predicted tokens are independent.

By Ian Li, Zilei Shao, Benjie Wang, Rose Yu, Guy Van den Broeck, Anji Liu

llms diffusion reinforcement-learning

Related stories

From Uniform to Learned Graph Priors: Diffusion for Structure Discovery

Learning $\mathsf{AC}^0$ under Locally Sampleable Graphical Models

Equivariant Neural Belief Propagation

Statistically Meaningful Geometry (SMG) Beyond the Euclidean Paradigm, with Application to Generative AI

Prior-Informed Flow Matching for Graph Reconstruction

Breaking the Factorization Barrier in Diffusion Language Models