arXiv Machine Learning August 27, 2026 By Kehan Wen, Ziming Li, Siyuan Luo, Fan Shi

JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics

Read the original on arXiv Machine Learning →

JEPA-x is a cross‑predictive physics grounding method that aligns visual latent dynamics with privileged physical trajectories. By treating visual observations and physical states as two views of the same action‑conditioned trajectory and sharing a predictor, it forces the model to learn a common transition rule for both modalities. The physical branch is only used during training, so deployment incurs no extra cost, and the approach significantly reduces rollout drift and boosts control success across a multi‑task suite.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 26

XP-JEPA: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics

arXiv:2608.24044v1 Announce Type: new Abstract: Latent world models plan by predicting how candidate actions transform learned representations. In self-predictive models, however, the encoder and pre...

By Kehan Wen, Ziming Li, Siyuan Luo, Fan Shi

arXiv AI

Sep 30

V-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents

arXiv:2609.37250v1 Announce Type: cross Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrai...

By Yang Zhang, Jiangyuan Zhao, Chenyou Fan, Jiayu Hu, Xiu Yuan, Chenjia Bai, Xiu Li

diffusion multimodal

arXiv AI

Aug 13

Foresight Without Seeing: Latent Futures for World Action Models

arXiv:2608. 11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction.

By Jiakai Huang, Zhongbo Wu, Zheng Zhang, Zihan Wang, Shan You, Tao Huang

diffusion robotics

arXiv Computer Vision

Oct 8

Juno: Taming Predictive Latents for Vision-Language-Action Models

arXiv:2610.09940v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) predict masked or future observations in representation space, offering a natural source of predicti...

By Yuchen Zhu, Chenyi Xu, Yulin Zhang, Gang Xu, Wentao Zhu

rag robotics fine-tuning multimodal

arXiv Machine Learning

Oct 3

JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts

JEPA‑TTT is a method that continuously adapts the latent dynamics predictor of a pretrained Joint‑Embedding Predictive Architecture (JEPA) world model during test time. It performs self‑supervised updates across episodes while keeping the visual encoder and reward head fixed, using dense replay to sample prediction windows from a growing buffer. In experiments on eight dynamics shifts across four continuous‑control environments, JEPA‑TTT reduces latent prediction error by 83% and improves planning performance by 153% compared to the frozen model.

By Zheyuan Zhang, Suyu Ye, Nakul Agarwal, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Daniel Khashabi, Tianmin Shu, Vaishnav Tadiparthi

rag agents

arXiv Computer Vision

Sep 10

Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization

arXiv:2609.10464v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning,...

By Andy Zeyi Liu, Haoran Sun, Lucas Baker, Randall Balestriero, John Sous

rag diffusion robotics