Hugging Face Trending Papers August 10, 2026

Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification

Read the original on Hugging Face Trending Papers →

Active inference offers a unified framework for perception, learning, and action, but scaling discrete active-inference models to rich spatial and temporal domains remains difficult. Renormalising generative models (RGMs) address this challenge by composing discrete generative models across spatial and temporal scales, coarse-graining lower-level states and paths into higher-level causes for objects, events, and action.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

benchmarks

arXiv AI

Aug 11

Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification

arXiv:2608. 09512v1 Announce Type: new Abstract: Active inference offers a unified framework for perception, learning, and action, but scaling discrete active-inference models to rich spatial and temporal domains remains difficult.

By Karim Zaghw, Andrew Pashea, Marc Pritsch, Wouter Nuijten, Karl Friston, Lancelot Da Costa

benchmarks

arXiv AI

Jun 9

ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning

arXiv:2505. 21457v2 Announce Type: replace-cross Abstract: Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information.

By Muzhi Zhu, Hao Zhong, Canyu Zhao, Zongze Du, Mingyu Liu, Zheng Huang, Anzhou Li, Hao Chen, Cheng Zou, Jingdong Chen, Ming Yang, Chunhua Shen

llms agents computer-vision reinforcement-learning robotics multimodal benchmarks

arXiv Machine Learning

Aug 6

Distributional Active Inference

arXiv:2601. 20985v2 Announce Type: replace Abstract: Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning.

By Abdullah Akg\"ul, Gulcin Baykal, Manuel Hau{\ss}mann, Mustafa Mert \c{C}elikok, Melih Kandemir

reinforcement-learning robotics benchmarks

arXiv Machine Learning

Jul 21

Learning Spatio-Temporal Foundation Models from Pure Synthetic Data

arXiv:2607. 16251v1 Announce Type: new Abstract: Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time.

By Yutong Feng, Shiyuan Piao, Yutong Xia, Xu Liu, Wenqi Fan, Fugee Tsung, See-Kiong Ng, Yuxuan Liang

diffusion benchmarks safety

arXiv Machine Learning

Aug 5

Information-Geometric Forward Policy Training in GFlowNets

arXiv:2608. 03967v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects, requiring only an unnormalised target density specified through a reward.

By Yordan Raykov, Rodrigo Veiga

arXiv Machine Learning

5d ago

Unifying Generative Models with Path Integrals

arXiv:2608. 12438v1 Announce Type: new Abstract: We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for a single master action.

By Ramon Winterhalder

diffusion safety

Related stories

Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification

ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning

Distributional Active Inference

Learning Spatio-Temporal Foundation Models from Pure Synthetic Data

Information-Geometric Forward Policy Training in GFlowNets

Unifying Generative Models with Path Integrals