Image de couverture de livre

ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xue, Haotian, Chen, Yipu, Ma, Liqian, Zhao, Zelin, Moukheiber, Lama, Zhu, Yuchen, Chen, Yongxin
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRI
par: Moukheiber, Lama, et autres
Publié: (2026)

Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
par: Chen, Yipu, et autres
Publié: (2024)

Laplacian Multi-scale Flow Matching for Generative Modeling
par: Zhao, Zelin, et autres
Publié: (2026)

Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities
par: Moukheiber, Dana, et autres
Publié: (2024)

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
par: Fan, Jiaojiao, et autres
Publié: (2024)

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
par: Xue, Haotian, et autres
Publié: (2024)

PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
par: Yang, Yunhan, et autres
Publié: (2026)

Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation
par: Long, Zeqian, et autres
Publié: (2026)

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
par: Wang, Chen, et autres
Publié: (2025)

DengueNet: Dengue Prediction using Spatiotemporal Satellite Imagery for Resource-Limited Countries
par: Kuo, Kuan-Ting, et autres
Publié: (2024)

ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
par: Chen, Yuzhi, et autres
Publié: (2026)

OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance
par: Wang, Cong, et autres
Publié: (2026)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
par: Ji, Sihui, et autres
Publié: (2025)

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
par: Xue, Haotian, et autres
Publié: (2023)

World Guidance: World Modeling in Condition Space for Action Generation
par: Su, Yue, et autres
Publié: (2026)

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
par: Xue, Haotian, et autres
Publié: (2025)

CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization
par: Zhao, Zelin, et autres
Publié: (2025)

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
par: Zhang, Tianyuan, et autres
Publié: (2024)

Toward effective protection against diffusion based mimicry through score distillation
par: Xue, Haotian, et autres
Publié: (2023)

OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation
par: Lin, Yuchen, et autres
Publié: (2025)

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models
par: Zhang, Qiyuan, et autres
Publié: (2026)

RealWonder: Real-Time Physical Action-Conditioned Video Generation
par: Liu, Wei, et autres
Publié: (2026)

PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance
par: Satish, Siddarth Nilol Kundur, et autres
Publié: (2026)

PhysGen3D: Crafting a Miniature Interactive World from a Single Image
par: Chen, Boyuan, et autres
Publié: (2025)

PhysGen: Physically Grounded 3D Shape Generation for Industrial Design
par: You, Yingxuan, et autres
Publié: (2025)

ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
par: Wang, Boyuan, et autres
Publié: (2026)

PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos
par: Cao, Meng, et autres
Publié: (2024)

MultiModal Action Conditioned Video Generation
par: Li, Yichen, et autres
Publié: (2025)

MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling
par: Zhang, Bowen, et autres
Publié: (2024)

PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding
par: Zhang, Haoze, et autres
Publié: (2025)

PhysVid: Physics Aware Local Conditioning for Generative Video Models
par: Pathak, Saurabh, et autres
Publié: (2026)

FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance
par: Shao, Dian, et autres
Publié: (2025)

iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
par: Fang, Jianjie, et autres
Publié: (2026)

PhysAnimator: Physics-Guided Generative Cartoon Animation
par: Xie, Tianyi, et autres
Publié: (2025)

VRAG: Learning World Models for Interactive Video Generation
par: Chen, Taiye, et autres
Publié: (2025)

PhysX-3D: Physical-Grounded 3D Asset Generation
par: Cao, Ziang, et autres
Publié: (2025)

MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration
par: Li, Guangyuan, et autres
Publié: (2025)

PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics
par: Zhou, Nan, et autres
Publié: (2025)

TKFNet: Learning Texture Key Factor Driven Feature for Facial Expression Recognition
par: Deng, Liqian
Publié: (2025)

PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis
par: Yang, Yu, et autres
Publié: (2025)