Imagen de Portada

Do generative video models understand physical principles?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Motamed, Saman, Culp, Laura, Swersky, Kevin, Jaini, Priyank, Geirhos, Robert
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Intriguing properties of generative classifiers
por: Jaini, Priyank, et al.
Publicado: (2023)

Video models are zero-shot learners and reasoners
por: Wiedemer, Thaddäus, et al.
Publicado: (2025)

Towards flexible perception with visual memory
por: Geirhos, Robert, et al.
Publicado: (2024)

Generative Models: What Do They Know? Do They Know Things? Let's Find Out!
por: Du, Xiaodan, et al.
Publicado: (2023)

Edge-preserving noise for diffusion models
por: Vandersanden, Jente, et al.
Publicado: (2024)

Navigating with Annealing Guidance Scale in Diffusion Space
por: Yehezkel, Shai, et al.
Publicado: (2025)

BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation
por: Hou, Xiaolu, et al.
Publicado: (2025)

Image Generation from Contextually-Contradictory Prompts
por: Huberman, Saar, et al.
Publicado: (2025)

PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers
por: Li, Songlin, et al.
Publicado: (2024)

LoMOE: Localized Multi-Object Editing via Multi-Diffusion
por: Chakrabarty, Goirik, et al.
Publicado: (2024)

Meta 3D Gen
por: Bensadoun, Raphael, et al.
Publicado: (2024)

Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries
por: Ouasfi, Amine, et al.
Publicado: (2024)

Towards Practical Single-shot Motion Synthesis
por: Roditakis, Konstantinos, et al.
Publicado: (2024)

Improving Video Generation with Human Feedback
por: Liu, Jie, et al.
Publicado: (2025)

Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
por: Lee, Seungyong, et al.
Publicado: (2025)

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
por: Dahary, Omer, et al.
Publicado: (2026)

GENIE: Gram-Eigenmode INR Editing with Closed-Form Geometry Updates
por: Karki, Samundra, et al.
Publicado: (2026)

Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer
por: Tsalakopoulos, Anastasios, et al.
Publicado: (2026)

TAUE: Training-free Noise Transplant and Cultivation Diffusion Model
por: Nagai, Daichi, et al.
Publicado: (2025)

Unsupervised Occupancy Learning from Sparse Point Cloud
por: Ouasfi, Amine, et al.
Publicado: (2024)

GAF-FusionNet: Multimodal ECG Analysis via Gramian Angular Fields and Split Attention
por: Qin, Jiahao, et al.
Publicado: (2024)

Boosting 3D Object Generation through PBR Materials
por: Wang, Yitong, et al.
Publicado: (2024)

Diffusion Self-Distillation for Zero-Shot Customized Image Generation
por: Cai, Shengqu, et al.
Publicado: (2024)

Infinite-Resolution Integral Noise Warping for Diffusion Models
por: Deng, Yitong, et al.
Publicado: (2024)

Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization
por: Fontana, Federico, et al.
Publicado: (2025)

Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observation
por: Billouard, Camille, et al.
Publicado: (2025)

PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF
por: Feng, Yutao, et al.
Publicado: (2023)

ArchComplete: Autoregressive 3D Architectural Design Generation with Hierarchical Diffusion-Based Upsampling
por: Rasoulzadeh, S., et al.
Publicado: (2024)

MotionV2V: Editing Motion in a Video
por: Burgert, Ryan, et al.
Publicado: (2025)

ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models
por: de Lutio, Riccardo, et al.
Publicado: (2026)

RealFill: Reference-Driven Generation for Authentic Image Completion
por: Tang, Luming, et al.
Publicado: (2023)

Teaching an Agent to Sketch One Part at a Time
por: Du, Xiaodan, et al.
Publicado: (2026)

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
por: Sani, Samin Mahdizadeh, et al.
Publicado: (2026)

FlexMotion: Lightweight, Physics-Aware, and Controllable Human Motion Generation
por: Tashakori, Arvin, et al.
Publicado: (2025)

Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects
por: Bensadoun, Raphael, et al.
Publicado: (2024)

Intrinsic PAPR for Point-level 3D Scene Albedo and Shading Editing
por: Moazeni, Alireza, et al.
Publicado: (2024)

COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models
por: Daiya, Divyanshu, et al.
Publicado: (2024)

Polyhedral Complex Derivation from Piecewise Trilinear Networks
por: Kim, Jin-Hwa
Publicado: (2024)

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
por: Sinha, Sankalp, et al.
Publicado: (2024)

3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
por: Gao, Yipeng, et al.
Publicado: (2026)