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:2608.24855v1 Announce Type: new
Abstract: Latent world models are inherently strong encoders that transform image pixel to latent embedding, yet existing world models still rely on online traje...
By Hsiang-Wei Huang, Jianxu Shangguan, Junbin Lu, Jenq-Neng Hwang
arXiv:2608.20974v1 Announce Type: cross
Abstract: Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent featu...
By Xinlin Wang, Yujiao Xiang, Yuheng Zhou, Jingqi Wang, Minqing Huang, Jiajie Huang, Dongxu Wei, Tingguang Zhou, Xiyang Wang, Gong Chen, Zhi Xu, Feiyang Tan, Hangning Zhou, Mu Yang
The paper introduces LeWAM, a bidirectional transformer that predicts forward, backward, inverse dynamics, and policy using a decoder‑free JEPA latent trained end‑to‑end. LeWAM’s latent representation aligns better with robot and object states than traditional reconstruction‑based world action models and ignores visual distractors more effectively. In closed‑loop experiments, LeWAM matches the performance of a flow‑matching policy while also providing a world model, and planning in the policy head’s noise space improves MPC performance compared to sampling raw actions.
By Shashank Hegde, Alexander Popov, Elie Aljalbout, Nikolai Smolyanskiy
arXiv:2606. 31232v1 Announce Type: new Abstract: Learning visual world models for planning requires compact latent dynamics that remain sensitive to actions, yet reconstruction-free joint-embedding objectives can collapse to action-insensitive representations.
By Zhenghao Zhang, Yuanxiang Wang, Zhenyu Guan, Yujia Yang, Bingkang Shi, Tianyu Zong, Hongzhu Yi, Guoqing Chao, Xingchen Chen, Tiankun Yang, Chenxi Bao, Tao Yu, Jingjing Zhou, Jungang Xu
arXiv:2606. 29059v1 Announce Type: cross Abstract: World modeling requires forecasting uncertain futures while preserving information useful for downstream perception.
By Francois Porcher, Nicolas Carion, Karteek Alahari, Shizhe Chen
SaiVLA-JEPA is a family of vision‑language‑action policies that condition on frozen V‑JEPA features and use lightweight auxiliary heads to predict future latent representations during training. Experiments on 10,030 LIBERO‑Plus episodes show that JEPA conditioning improves success rates to about 82.5% versus 71.6% without JEPA, but adding future supervision does not yield a detectable aggregate gain. Variants that adapt latent context or selected parameters provide mixed results, suggesting that latent‑prediction objectives should be evaluated via closed‑loop rollouts rather than latent loss alone.
By Rufeng Xiao (VLA Research Team, Synthoid.ai), Ruihao Xiao (VLA Research Team, Synthoid.ai), Wei Chen (VLA Research Team, Synthoid.ai), Xinhai Sun (VLA Research Team, Synthoid.ai)
LeWAM is a bidirectional transformer that predicts forward, backward, inverse dynamics and policy, trained end‑to‑end on a decoder‑free JEPA latent. It outperforms a forward‑only JEPA world model by better aligning latent representations with robot and object states while ignoring visual distractors. In closed‑loop tests, LeWAM matches a flow‑matching policy of the same size and improves MPC planning by sampling actions in the policy head’s noise space rather than raw actions.
By Shashank Hegde, Alexander Popov, Elie Aljalbout, Nikolai Smolyanskiy
The paper introduces Action-Contrastive Masked Transition Modeling (AC‑MTM), a method that stabilizes Joint‑Embedding Predictive Architectures (JEPAs) without relying on Gaussian regularization. AC‑MTM adds a training‑only inverse‑dynamics head that uses Action‑NCE to force each latent transition to identify its generating action, thereby preventing encoder collapse. Experiments on pixel‑control and multi‑object visual tasks show that AC‑MTM trains stably from scratch and matches or surpasses the performance of SIGReg, achieving up to a 24‑point improvement on the OGBench Visual Scene benchmark.
Variational Streaming Flow (VSF) extends the efficient Streaming Flow (SF) framework by learning a latent distribution conditioned on system dynamics, enabling probabilistic forecasting in physical time. Unlike SF’s deterministic velocity field, VSF produces multiple plausible future trajectories, improving predictive accuracy and distributional fidelity across deterministic and stochastic dynamical systems. The method supports long‑horizon rollouts over 1,000 steps, handles bifurcating dynamics, and can be integrated as a plug‑and‑play predictor into Joint‑Embedding Predictive Architecture (JEPA) world models to enhance navigation, motion planning, and manipulation tasks.
By Hans Hao-Hsun Hsu, Minseon Gwak, Soon Hoe Lim, Pan Li, N. Benjamin Erichson
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
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