arXiv:2607. 22430v1 Announce Type: new Abstract: Learning world models that infer environment dynamics from high-dimensional observations and predict outcomes under candidate actions is central to planning and control.
By Xiangteng Zhang, Yang Guan, Bo Zhang, Ya-Qin Zhang, Shengbo Eben Li
The paper introduces DSReg, a method that provably recovers individual world latent variables without relying on reconstruction, decoders, or labels. It leverages a Structural Diversity condition—distinct dependency footprints of different latents—to achieve full identifiability up to signed permutation. DSReg can be applied post hoc to any linearly identified representation, preserving dense prediction while improving latent recovery across synthetic and real-world experiments.
By Yujia Zheng, David Klindt, Randall Balestriero, Bernhard Sch\"olkopf
arXiv:2608.29029v3 Announce Type: replace-cross
Abstract: Joint-Embedding Predictive Architectures (JEPAs) provide a powerful framework for latent world modeling and planning in a reconstruction-free...
By Yanchen Huo, Ziying Song, Yadan Luo
arXiv:2610.32657v1 Announce Type: new
Abstract: Decision Transformer (DT) has demonstrated strong performance in various offline reinforcement learning (RL) tasks by conditioning action generation on...
By Changxu Ni, Yiyang Ni, Jun Li, Feiran You, Hongyang Du, Haitao Zhao, Shi Jin
arXiv:2608. 13621v1 Announce Type: new Abstract: A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emission back to observation space.
By Yongchao Huang
arXiv:2610.42096v1 Announce Type: cross
Abstract: World action models (WAMs) learn latent variables from observations and use these to both predict the evolution of the scene and to generate actions....
By Juntao Cheng, Jinzhou Tang, Fan Feng, Henrik I. Christensen, Yujia Zheng
SplitJEPA is a new joint embedding predictive architecture that learns a latent state and its invariant and variant components directly in representation space, without reconstructing observations. The method proves that, under stationary Gaussian predictive dynamics and a full‑rank variation condition, it can identify the invariant and variant subspaces up to independent block‑wise isometries. Experiments on synthetic nonlinear systems and robotic manipulation tasks confirm the theoretical guarantees and demonstrate practical benefits for robustness and efficiency.
By Ruijin Hua, Zichuan Liu, Zhuokai Zhao, Yujia Zheng
The paper investigates how encouraging action predictability in latent world models can preserve intrinsic dynamics, which are crucial for planning. By deriving a theoretical lower bound and conducting empirical tests, the authors show that action predictability prevents the encoder from merging distinct action outcomes, even when visual appearance varies. Using a method called Concat IDM, they achieve a substantial increase in planning success on the Push‑T benchmark, from 9.1% to 77.2%, demonstrating the practical benefit of this inductive bias.
By Jiamin Shi, Yuanhong Zhang, Zhiyang Liu, Jiawei Sun, Jingwen Fu
MOSAIC is a sparse temporal variational autoencoder that merges causal representation learning with support recovery to identify interpretable latent modules in scientific time series. It leverages regime‑conditioned temporal variation to discover latent variables and uses an additive decoder to recover a sparse set of observations linked to each latent, providing module‑level interpretability. The method offers theoretical guarantees for ANOVA main‑effect identifiability under smooth mixing functions and demonstrates empirical success across diverse domains such as RNA dynamics, solar wind, ENSO climate, industrial process control, and synthetic tokamak data.
By Shicheng Fan, Nour Elhendawy, Jianle Sun, Ke Fang, Kun Zhang, Yihang Wang, Lu Cheng
arXiv:2605. 15995v2 Announce Type: replace-cross Abstract: Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems.
By Gwenol\'e Quellec
Flow-JEPA introduces a conditional flow matching dynamics model that generates a sequence of future latent states conditioned on current observations and actions, replacing deterministic autoregressive prediction with stochastic trajectory-level prediction. By using a Gaussian flow source, the model learns to transport perturbed latent trajectories toward clean future representations while remaining within the reconstruction‑free JEPA framework. The approach improves mean success rates from 86% to 92% under clean observations and from 67% to 86% under noisy conditions.
By Yanchen Huo, Ziying Song, Yadan Luo
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.
By Kehan Wen, Ziming Li, Siyuan Luo, Fan Shi