4DSynth is a controllable procedural system that transforms natural-language descriptions, blueprint masks, or single photographs into editable 4D environments featuring explicit geometry, animated actors, collision-free trajectories, and physics-ready simulation states. The system unifies animation, camera planning, rendering, and task generation within a single geometry-grounded representation, enabling scalable creation of diverse, interactive scenes. Using 4DSynth, the authors built 4DSynth-Nav, an interactive navigation benchmark that demonstrates the reproducibility of failures and tunable difficulty across three tiers for vision‑language models.
arXiv:2607. 21522v1 Announce Type: cross Abstract: Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging.
By Hongxin Zhang, Chunru Lin, Junyan Li, Zhou Xian, Tsun-Hsuan Wang, Chuang Gan
arXiv:2607. 01766v1 Announce Type: new Abstract: LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output.
By Chunjiang Liu, Xiaoyuan Wang, Haoyu Chen, Yizhou Zhao, Ming-Hsuan Yang, L\'aszl\'o A. Jeni
LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output. Dynamic 4D scenes from text alone, in which liquids flow, particles emit, rigid bodies cascade, and articulated mechanisms move, remain largely unexplored despite their value as editable content and as physics-grounded training data for video generation and embodied AI.
arXiv:2610.20560v1 Announce Type: cross
Abstract: 3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence...
By Weichen Lyu, Chong Xia, Mingyu Dong, Long Xu, Shengjun Zhang, Yueqi Duan
arXiv:2606. 06390v1 Announce Type: cross Abstract: Indoor scene generation is crucial for robot simulation and modern interior design.
By Wenbo Li, Xiaoliang Ju, Zipeng Qin, Rongyao Fang, Hongsheng Li
The paper introduces the World-Ego Model (WEM), which separates an embodied video into a background‐only world component and an ego component comprising the robot and manipulated objects. By using role‑conditioned attention and asymmetric query budgets for state prediction, coupled with a semantic‑routed mixture‑of‑experts diffusion generator, WEM disentangles the generation of scene evolution and instruction following. The authors also release HTEWorld, a large dataset of 125K training clips and 300 evaluation trajectories for long‑horizon navigation‑manipulation tasks, and demonstrate that WEM outperforms prior methods on this benchmark.
By Zuyao Lin, Jianhui Zhang, Peidong Jia, Xiaoguang Zhao, Shanghang Zhang, Jingdong Wang, Xingyu Chen
arXiv:2610.04432v2 Announce Type: replace
Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on...
By Jinzhou Tang, Zijun Zhang, Jing Yang, Yuchen Yan, Kun Zhou, Lingjun Mao, Ruobing Han, Jinglin Cao, Wenpeng Xu, Lukun He, Minghao Fu, Fan Feng, Biwei Huang
3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models. Previous methods either leve...
Edit4D is a new text‑to‑4D scene generation framework that builds editable 4D scenes by separately modeling background and dynamic characters. It decomposes user instructions into stage‑specific prompts for background, character, and composition, then uses text‑to‑image, camera‑conditioned priors, and image‑conditioned video priors to synthesize multi‑view images, reconstruct 3D Gaussian splatting backgrounds, animate characters into 4D meshes, and finally compose and refine the scene with text‑guided segmentation and contact‑aware optimization. This pipeline allows controllable camera motion, flexible object‑level editing, and practical construction of editable 4D scenes.
By Chanwoo Kim, Tackgeun You, Hwasup Lim
arXiv:2606. 00095v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions.
By Kailing Li, Tianwen Qian, Lijin Yang, Yuqian Fu, Jingyu Gong, Xiaoling Wang, Liang He
arXiv:2608.18734v2 Announce Type: replace
Abstract: 4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vis...
By Kumal Hewagamage, Isuranga Senavirathne, Sasika Amarasinghe, Hasitha Gallella, Dulanga Weerakoon, Vigneshwaran Subbaraju, Ranga Rodrigo