The paper introduces DRILL, a bilevel training framework that optimizes world models for policy improvement rather than pixel accuracy. By reweighting prediction errors with policy visitation and confidence (DRILL‑VWI) or using a full meta‑gradient approach (DRILL‑IMG), the authors demonstrate significant gains in downstream policy success rates across multiple manipulation simulators. The work shows that world models can be more effectively trained using the policy gradients they generate, rather than relying solely on pixel‑level prediction metrics.
By Zhaolu Kang, Tailong Luo, Lei Wei, Guangyuan Dong, Sihan Liu, Yingjie He, Siheng Wang, Shuaibo Li, Rongchao Zhang, Zhen Tian, Richeng Xuan, Zhichao Hu
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
arXiv:2602. 13977v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots.
By Zhennan Jiang, Shangqing Zhou, Yutong Jiang, Zefang Huang, Mingjie Wei, Yuhui Chen, Tianxing Zhou, Zhen Guo, Hao Lin, Quanlu Zhang, Yu Wang, Haoran Li, Chao Yu, Dongbin Zhao
The paper introduces QWM, a framework that integrates world models with standard Q‑learning to perform test‑time search over imagined trajectories. By training the policy and value function solely on real transitions, QWM avoids compounding model bias while still benefiting from predictive search. Experiments on the Robomimic and LIBERO manipulation benchmarks show that QWM outperforms strong prior state‑of‑the‑art methods in both sample efficiency and performance.
By Perry Dong, Yueru Jia, Chelsea Finn, Dorsa Sadigh
arXiv:2610.36925v1 Announce Type: new
Abstract: Learning from experience is essential for building the next generation of agents that continually expand their capabilities. Pretrained vision-language...
By Haoxi Li, Sikai Bai, Jianfei Ma, Qinglin Hou, Xiaocheng Lu, Tao Han, Jie Zhang, Song Guo
The paper introduces a reinforcement learning post‑training scheme that trains robot world models on their own autoregressive rollouts, using a contrastive RL objective adapted from diffusion models. It also proposes a training protocol that compares multiple variable‑length futures, a multi‑view visual fidelity reward, and demonstrates state‑of‑the‑art rollout fidelity on the DROID dataset, outperforming baselines on LPIPS, SSIM, and human preference tests.
By Jai Bardhan, Patrik Drozdik, Josef Sivic, Vladimir Petrik
arXiv:2610.27851v1 Announce Type: cross
Abstract: This paper shows that JEPA-style latent world models (LWMs) can learn across diverse domains and data sources by adopting the language-conditioned in...
By Junha Song, Geonmo Gu, Jeongeun Park, Heejeong Nam, Lucas Maes, Byeongho Heo, Dongyoon Han, Sangdoo Yun
arXiv:2604. 16557v2 Announce Type: replace Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).
By Yuming Yan, Kai Tang, Sihong Chen, Ke Xu, Dan Hu, Qun Yu, Pengfei Hu
arXiv:2607. 15142v1 Announce Type: new Abstract: World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation.
By Yukuan Lu, Zaishuo Xia, Weyl Lu, Yubei Chen
WorldGuide is a closed‑loop video world model that, given an initial image and a task goal, predicts an atomic action, generates the corresponding video clip, and uses that clip to decide the next action or terminate the task. It trains a Planner to predict the next action or completion from visual progress and an Executor to realize those actions, while a hierarchical visual memory tracks state over long horizons. The authors introduce WorldGuide‑Bench, a dataset of ~59K step‑annotated videos across 245 tasks, and show that WorldGuide outperforms the recent MiniMax‑H3 model on both WorldGuide‑Bench and VideoCraft‑Bench, highlighting the benefit of coupling planning with learned execution for goal‑directed procedural video generation.
By Ankan Deria, Komal Kumar, Hisham Cholakkal, Fahad Shahbaz Khan, Salman Khan
PAVXploreRL introduces a reinforcement learning framework that builds on a pretrained latent world model to explicitly optimize Physical Plausibility, Action Adherence, and Visual Fidelity (PAV) objectives. By combining in‑distribution expert trajectories with noise‑driven out‑of‑distribution action exploration, the method avoids reliance on paired video supervision and improves generalization. Experiments demonstrate a 5.6% average performance gain over pretrained baselines and more reliable policy evaluation with reduced overestimation bias.
By Han Wang, Zijun Wang, Shuoshuo Xue, Rui Cao, Fengjiao Chen, Xiaodan Liang, Roy Ka-Wei Lee
arXiv:2610.37219v1 Announce Type: new
Abstract: The vision-language-action (VLA) and world-action model (WAM) communities debate whether control policies should inherit pretrained knowledge from visi...
By Yonghao Yu, Lang Huang, Runyi Li, Toshihiko Yamasaki