通过逆向动力学预测改进用于世界建模的VLM

报道来源 [4]

1. arXiv cs.AI TIER_1 English(EN) · Yifu Qiu, Yftah Ziser, Anna Korhonen, Shay B. Cohen, Edoardo M. Ponti · 2026-06-04 04:00

   VLMs 能预测未来状态吗？从逆向动力学引导世界模型

   arXiv:2506.06006v3 Announce Type: replace-cross Abstract: Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.e., predicting the future state (in image form) given the previous observation and an action (in language form)? We find that VLMs stru…

2. arXiv cs.AI TIER_1 English(EN) · Yuejiang Liu, Fan Feng, Lingjing Kong, Weifeng Lu, Jinzhou Tang, Kun Zhang, Kevin Murphy, Chelsea Finn, Yilun Du · 2026-06-01 04:00

   World Action Verifier：通过前向-逆向不对称实现自改进的世界模型

   arXiv:2604.01985v2 Announce Type: replace-cross Abstract: General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learning which primarily focuses on optimal act…

3. arXiv cs.CV TIER_1 English(EN) · Ao Liang, Lingdong Kong, Tianyi Yan, Hongsi Liu, Wesley Yang, Ziqi Huang, Wei Yin, Jialong Zuo, Yixuan Hu, Dekai Zhu, Dongyue Lu, Youquan Liu, Guangfeng Jiang, Linfeng Li, Xiangtai Li, Long Zhuo, Lai Xing Ng, Benoit R. Cottereau, Changxin Gao, Liang Pan,… · 2026-06-02 04:00

   WorldLens：对真实世界驾驶世界模型的全谱评估

   arXiv:2512.10958v2 Announce Type: replace Abstract: Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a u…

4. arXiv cs.CV TIER_1 English(EN) · An Dinh Vuong, Tuan Van Vo, Abdullah Sohail, Haoran Ding, Liang Ma, Xiaodan Liang, Anqing Duan, Ivan Laptev, Ian Reid · 2026-06-01 04:00

   World2Act：基于世界模型动态的潜在动作后训练

   arXiv:2603.10422v2 Announce Type: replace Abstract: World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene variation. However, most WM-based post-training…