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.
The paper introduces Action-Contrastive Masked Transition Modeling (AC‑MTM), a method that replaces the Gaussian regularizer used in Joint‑Embedding Predictive Architectures (JEPAs) with a contrastive inverse‑dynamics head. AC‑MTM trains a forward latent‑prediction model while an auxiliary inverse‑dynamics task forces the encoder to distinguish actions from latent transitions, preventing collapse without requiring a target network or reconstruction loss. Experiments on pixel‑control and multi‑object visual tasks show that AC‑MTM matches or surpasses the performance of the Gaussian‑based SIGReg regularizer, achieving up to 20–24 point improvements on the OGBench Visual Scene benchmark.
By Jack Boylan, Chris Hokamp
arXiv:2606. 05328v1 Announce Type: cross Abstract: Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators.
By Parsa Esmati, Somjit Nath, Katja Hofmann, Derek Nowrouzezahrai, Samira Ebrahimi Kahou, Majid Mirmehdi
arXiv:2609.27455v1 Announce Type: new
Abstract: World Action Models (WAMs) jointly model action generation and environment dynamics and are mostly built on pretrained Video Diffusion Models (VDMs). I...
By Xueji Fang, Boqiang Duan, Hua Wu, Jingdong Wang, Guo-Jun Qi
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
arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.
By Jewon Yeom, Hanseul Kim, Jeongjae Park, Sungmok Jung, Jaejin Lee, Taesup Kim
TT-VidT is a video pretraining method that decouples the temporal axis by combining a per‑frame ViT-B/16 spatial encoder with a compact Temporal Transfer Layer trained via Diff Compression. The authors conduct a systematic 24‑configuration study to isolate architecture, objective, and decoder effects, showing that the full TT-VidT design yields the strongest motion‑sensitive representations. In downstream fine‑tuning, TT‑VidT outperforms state‑of‑the‑art baselines on Jester, Something‑Something V2, ARID, and Diving48 while using significantly fewer encoder FLOPs.
By Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai
arXiv:2608. 11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction.
By Jiakai Huang, Zhongbo Wu, Zheng Zhang, Zihan Wang, Shan You, Tao Huang
arXiv:2603. 14294v3 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility?
By Chujun Tang, Lei Zhong, Fangqiang Ding
arXiv:2608. 01049v1 Announce Type: cross Abstract: World models have attracted significant attention for their ability to capture and predict the structure and dynamics of the physical world.
By Kapil Wanaskar, Gaytri Jena, Aman Chadha, Vinija Jain, Vasu Sharma, Amitava Das
The paper argues that diffusion-based action policies can use a frozen, observation‑free backbone as a reusable trajectory prior, with task adaptation handled entirely by the conditioning pathway. By pretraining a general action head on forward‑kinematics data and then freezing it, the authors show that a single backbone can match or outperform normally trained models on MimicGen and LIBERO. Their experiments reveal that a small 5 M‑parameter MLP backbone can rival large U‑Net and transformer backbones, indicating that action backbones are often over‑parameterized and that image‑style architectures may not be the best fit for low‑dimensional action generation.
By Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li, Gengze Zhou, Qi WU
arXiv:2607. 20628v1 Announce Type: cross Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction.
By Renbiao Jin, Mingxin Yang, Yutian Chen, Junhao Zhuang, Xin Cai, Mulin Yu, Linning Xu, Wenxian Yu, Danping Zou, Shi Guo, Tianfan Xue