ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912984819826688 |
|---|---|
| author | Chen, Yuzhi Chen, Ronghan Huo, Dongjie Yang, Yandan Qi, Dekang Liu, Haoyun Lin, Tong Zeng, Shuang Xiao, Junjin Chang, Xinyuan Xiong, Feng Wei, Xing Ma, Zhiheng Xu, Mu |
| author_facet | Chen, Yuzhi Chen, Ronghan Huo, Dongjie Yang, Yandan Qi, Dekang Liu, Haoyun Lin, Tong Zeng, Shuang Xiao, Junjin Chang, Xinyuan Xiong, Feng Wei, Xing Ma, Zhiheng Xu, Mu |
| contents | Video-based world models offer a powerful paradigm for embodied simulation and planning, yet state-of-the-art models often generate physically implausible manipulations - such as object penetration and anti-gravity motion - due to training on generic visual data and likelihood-based objectives that ignore physical laws. We present ABot-PhysWorld, a 14B Diffusion Transformer model that generates visually realistic, physically plausible, and action-controllable videos. Built on a curated dataset of three million manipulation clips with physics-aware annotation, it uses a novel DPO-based post-training framework with decoupled discriminators to suppress unphysical behaviors while preserving visual quality. A parallel context block enables precise spatial action injection for cross-embodiment control. To better evaluate generalization, we introduce EZSbench, the first training-independent embodied zero-shot benchmark combining real and synthetic unseen robot-task-scene combinations. It employs a decoupled protocol to separately assess physical realism and action alignment. ABot-PhysWorld achieves new state-of-the-art performance on PBench and EZSbench, surpassing Veo 3.1 and Sora v2 Pro in physical plausibility and trajectory consistency. We will release EZSbench to promote standardized evaluation in embodied video generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23376 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment Chen, Yuzhi Chen, Ronghan Huo, Dongjie Yang, Yandan Qi, Dekang Liu, Haoyun Lin, Tong Zeng, Shuang Xiao, Junjin Chang, Xinyuan Xiong, Feng Wei, Xing Ma, Zhiheng Xu, Mu Computer Vision and Pattern Recognition Robotics Video-based world models offer a powerful paradigm for embodied simulation and planning, yet state-of-the-art models often generate physically implausible manipulations - such as object penetration and anti-gravity motion - due to training on generic visual data and likelihood-based objectives that ignore physical laws. We present ABot-PhysWorld, a 14B Diffusion Transformer model that generates visually realistic, physically plausible, and action-controllable videos. Built on a curated dataset of three million manipulation clips with physics-aware annotation, it uses a novel DPO-based post-training framework with decoupled discriminators to suppress unphysical behaviors while preserving visual quality. A parallel context block enables precise spatial action injection for cross-embodiment control. To better evaluate generalization, we introduce EZSbench, the first training-independent embodied zero-shot benchmark combining real and synthetic unseen robot-task-scene combinations. It employs a decoupled protocol to separately assess physical realism and action alignment. ABot-PhysWorld achieves new state-of-the-art performance on PBench and EZSbench, surpassing Veo 3.1 and Sora v2 Pro in physical plausibility and trajectory consistency. We will release EZSbench to promote standardized evaluation in embodied video generation. |
| title | ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2603.23376 |