EvoWorld introduces a framework that couples a vision‑language model with a segment‑autoregressive video renderer to enable generative video models to reason about world evolution beyond visual fidelity. The system maintains an evolving account of the world, infers event consequences, and renders causally plausible outcomes even when events occur out of sight. The accompanying EvoWorld‑Data and EvoWorld‑Bench datasets provide training and evaluation for event realization, causal reactions, and revisit consistency.
By Yequan Bie, Dengyang Jiang, Zhixuan Chen, Xiaozhuan Liang, Haoxuan Che, Quande Liu, Xi Chen, Hao Chen
StateCraft introduces a new architecture that separates a persistent, updatable abstract state from the visual state in video world models. By pairing a language model with a video diffusion model, it tracks entity changes over time and conditions visual generation on this abstract state. The approach is evaluated on generative interfaces and a new benchmark, showing improved generation quality, memory usage, and controllability, while enabling direct editing of unseen states and extending to spatial 3D environments.
By Lorenzo Venturoli, Nedko Savov, Xi Wang, Marc Pollefeys, Luc Van Gool
arXiv:2608. 08982v1 Announce Type: new Abstract: Interactive video world models generate rollouts autoregressively under an action stream, yet they are trained and evaluated almost exclusively on factual prediction.
By Yu Ma, Hongli Shi, Xinran Xu
arXiv:2606. 24152v1 Announce Type: cross Abstract: Existing literature claims that video generation essentially is world modelling.
By Xin Wang, Wenxuan Liu, Tongtong Feng, Wenwu Zhu
arXiv:2606. 00267v1 Announce Type: cross Abstract: Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot actions.
By Junwon Seo, Sushant Veer, Ran Tian, Wenhao Ding, Apoorva Sharma, Karen Leung, Edward Schmerling, Marco Pavone, Andrea Bajcsy
arXiv:2610.34663v1 Announce Type: cross
Abstract: Video world models trained on large-scale robot data promise a safe and scalable approach for learning and evaluating policies that act in the physic...
By Mattia Scardecchia, Sherry Yang
arXiv:2610.07922v1 Announce Type: cross
Abstract: World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, su...
By Heng Yu, David D. Yuan, Juze Zhang, Changan Chen, Yao Feng, Michelle Baldonado, Steve Cousins, Li Fei-Fei, Jiajun Wu, Ehsan Adeli
The paper surveys recent progress in video foundation and world models, framing both as ways to relate video observations to an evolving latent world. It categorizes the literature into four operations—reading, writing, sharing, and interacting—highlighting how each addresses different aspects of understanding, generating, integrating, and updating world states from video. The authors trace a shift from clip‑level recognition toward persistent, controllable, and physically valid world representations, and outline remaining challenges.
By Shengqiong Wu, Meng Luo, Bobo Li, Ziwei Liu, Shuicheng Yan, Ming-Hsuan Yang, Philip Torr, Hao Fei
The paper introduces CADRE, a family of causal diffusion representation autoencoders designed for video world models that balance spatio‑temporal compression. By training the same world model across different CADRE variants in manipulation and navigation tasks, the authors map the latency‑quality trade‑off and uncover that strong compression favors diffusion decoders, temporal compression is more effective in the autoencoder for manipulation, and spatial compression is preferable when the camera moves. The study also reveals that coarse spatial tokens degrade motion perception more than image quality when the camera is static.
By Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour, Patrick P\'erez, David Picard
CounterVid introduces a scalable counterfactual video generation framework that creates videos differing only in actions or temporal structure while keeping scene context intact. The approach uses multimodal LLMs for action proposals and diffusion models for editing, producing a synthetic dataset of ~26k preference pairs for action recognition and sequence ordering. With the MixDPO optimization method, the authors demonstrate significant improvements in action recognition and temporal ordering on Qwen2.5‑VL and InternVL3 backbones, while maintaining overall video understanding.
By Tobia Poppi, Burak Uzkent, Amanmeet Garg, Lucas Porto, Garin Kessler, Yezhou Yang, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara, Florian Schiffers
World in World introduces a training‑free, inference‑time interface that transforms diverse control signals—such as source‑video observations, target‑view projections, geometry renderings, and retrieved states—into camera‑ and time‑labelled visual states. These states are processed by a frozen causal video model’s self‑attention, enabling tasks like camera‑controlled rerendering, long‑horizon revisiting, and human‑motion transfer without additional training. The method employs a correspondence router and evidence‑wise attention to align token identities and regulate auxiliary channel contributions during a single denoising pass.
By Chenxi Song, Yanming Yang, Chi Zhang
World in World introduces a training‑free inference interface that lets users control autoregressive video world models from new viewpoints. By converting diverse control signals—source‑video observations, target‑view projections, geometry renderings, and retrieved states—into camera‑ and time‑labelled visual tokens, the system uses a frozen causal video model’s self‑attention to maintain synchronization, complete unseen regions, and recover past appearances. The method supports camera‑controlled rerendering, long‑horizon revisiting, and human‑motion transfer while preserving perceptual quality, temporal consistency, and camera‑following accuracy.