arXiv:2603. 02650v2 Announce Type: replace-cross Abstract: Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inconsistent with the environment dynamics, resulting in brittle execution.
By Yuan Lu, Dongqi Han, Yansen Wang, Dongsheng Li
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:2609.37113v1 Announce Type: new
Abstract: Generalized reaction-diffusion systems encompass diverse transport mechanisms and coupled reaction kinetics. A central question for neural PDE solvers...
By Shang-Ke Chen, Yu-Peng Wang, Shih-Hsuan Hung, Wei-Fang Sun, Chao-Shun Zhan, Simon See, Min-Jhe Lu
ForeDrive introduces a planning-relevant latent world model that is asymmetrically coupled to a Diffusion Transformer planner. The model learns multi‑horizon latent futures with a JEPA‑style world model, while planning gradients update the shared encoder and stop‑gradient routing trains the predictor with forecasting losses only. Gated visual fusion, future‑status injection, and Trajectory‑Adaptive Bias are used to guide trajectory generation without overriding current observations, achieving high performance on NAVSIM benchmarks using only front‑view images and pure imitation learning.
By Sinuo Wang, Zichong Gu, Yuhan Huang, Wenxin Wen, Xun Yang, Yiqing Zhang, Xingyu Zhang, Ningyu Che, Jie Ling, Qiankun Yu, Wei Liu, Jing Xu, Xinggang Wang
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
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