arXiv Machine Learning June 24, 2026 By Mohammed Nagdi, Evangelos-Marios Nikolados, Alexey Yermakov, Mars Gao, Nathan Kutz, Filippo Menolascina

Learning the Koopman Operator using Attention Free Transformers

Read the original on arXiv Machine Learning →

arXiv:2606. 23957v1 Announce Type: new Abstract: Learning Koopman operators with autoencoders enables linear prediction in a latent space, but long-horizon rollouts often drift off the learned manifold, leading to phase and amplitude errors on systems with switching, continuous spectra, or strong transients.

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

arXiv AI

Jul 10

The Phasor Transformer: Resolving Attention Bottlenecks on the Unit Circle

arXiv:2603. 17433v2 Announce Type: replace-cross Abstract: Transformer models have redefined sequence learning, yet dot-product self-attention introduces a quadratic token-mixing bottleneck for long-context time-series.

By Dibakar Sigdel

llms benchmarks

arXiv Machine Learning

Jun 26

Fast LeWorldModel

arXiv:2606. 26217v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs), including recent LeWorldModel (LeWM), have become a promising foundation for reconstruction-free visual world models.

By Yuntian Gao, Xiangyu Xu

rag

arXiv AI

Aug 3

FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

arXiv:2607. 29235v1 Announce Type: cross Abstract: Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real observations--not recursive rollout.

By Peize Li, Ruimeng Zhang, Ru Zhang, Cong Huang, Kai Chen, Shanghang Zhang

diffusion robotics efficiency

arXiv Machine Learning

Jul 23

Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination

arXiv:2607. 19719v1 Announce Type: new Abstract: Latent world models improve sample efficiency in continuous control by optimizing policies over imagined latent trajectories, but common neural transitions offer limited direct control over modal persistence and error accumulation in long rollouts.

By Jiaqi Li, Xinglong Zhang, Haibin Xie, Yixing Lan, Wei Pan, Xin Xu

agents

arXiv Machine Learning

Aug 10

Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction

arXiv:2608. 07420v1 Announce Type: new Abstract: World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions.

By Xinyi Li, Zaishuo Xia, Chenjie Hao, Yubei Chen

rag benchmarks

arXiv AI

Jul 9

Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization

arXiv:2604. 01577v3 Announce Type: replace-cross Abstract: We study out of distribution generalization in streaming tasks where models are trained on short sequences but must operate over much longer, unknown horizons under bounded memory.

By Shota Takashiro, Masanori Koyama, Takeru Miyato, Yusuke Iwasawa, Yutaka Matsuo, Kohei Hayashi

llms reinforcement-learning safety

Related stories

The Phasor Transformer: Resolving Attention Bottlenecks on the Unit Circle

Fast LeWorldModel

FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination

Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction

Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization