Imagen de Portada

Back to the Features: DINO as a Foundation for Video World Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Baldassarre, Federico, Szafraniec, Marc, Terver, Basile, Khalidov, Vasil, Massa, Francisco, LeCun, Yann, Labatut, Patrick, Seitzer, Maximilian, Bojanowski, Piotr
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
por: Terver, Basile, et al.
Publicado: (2025)

Learning Latent Action World Models In The Wild
por: Garrido, Quentin, et al.
Publicado: (2026)

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
por: Zhou, Gaoyue, et al.
Publicado: (2024)

Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
por: Raugel, Joséphine, et al.
Publicado: (2026)

Learning by Reconstruction Produces Uninformative Features For Perception
por: Balestriero, Randall, et al.
Publicado: (2024)

Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach
por: Vo, Huy V., et al.
Publicado: (2024)

DINOv3
por: Siméoni, Oriane, et al.
Publicado: (2025)

Fast and Exact Enumeration of Deep Networks Partitions Regions
por: Balestriero, Randall, et al.
Publicado: (2024)

Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence
por: Dawid, Anna, et al.
Publicado: (2023)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
por: Balestriero, Randall, et al.
Publicado: (2025)

Hierarchical Planning with Latent World Models
por: Zhang, Wancong, et al.
Publicado: (2026)

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
por: Zadaianchuk, Andrii, et al.
Publicado: (2023)

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
por: Assran, Mido, et al.
Publicado: (2025)

Disentangling the Factors of Convergence between Brains and Computer Vision Models
por: Raugel, Joséphine, et al.
Publicado: (2025)

Video Representation Learning with Joint-Embedding Predictive Architectures
por: Drozdov, Katrina, et al.
Publicado: (2024)

You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
por: Moutakanni, Théo, et al.
Publicado: (2024)

DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
por: Jose, Cijo, et al.
Publicado: (2024)

Cluster and Predict Latent Patches for Improved Masked Image Modeling
por: Darcet, Timothée, et al.
Publicado: (2025)

LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
por: Huang, Hai, et al.
Publicado: (2025)

Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
por: Huang, Hai, et al.
Publicado: (2026)

Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
por: Dupoux, Emmanuel, et al.
Publicado: (2026)

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations
por: Mialon, Grégoire, et al.
Publicado: (2022)

A hierarchical loss and its problems when classifying non-hierarchically
por: Wu, Cinna, et al.
Publicado: (2017)

Navigation World Models
por: Bar, Amir, et al.
Publicado: (2024)

OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
por: Goswami, Raktim Gautam, et al.
Publicado: (2025)

Parallel Stochastic Gradient-Based Planning for World Models
por: Psenka, Michael, et al.
Publicado: (2026)

Efficient Universal Perception Encoder
por: Zhu, Chenchen, et al.
Publicado: (2026)

A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
por: Terver, Basile, et al.
Publicado: (2026)

Causal-JEPA: Learning World Models through Object-Level Latent Masking
por: Nam, Heejeong, et al.
Publicado: (2026)

DINOv2: Learning Robust Visual Features without Supervision
por: Oquab, Maxime, et al.
Publicado: (2023)

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
por: Maes, Lucas, et al.
Publicado: (2026)

Revisiting Feature Prediction for Learning Visual Representations from Video
por: Bardes, Adrien, et al.
Publicado: (2024)

URLOST: Unsupervised Representation Learning without Stationarity or Topology
por: Yun, Zeyu, et al.
Publicado: (2023)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
por: Balestriero, Randall, et al.
Publicado: (2025)

The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
por: Sun, Shangwen, et al.
Publicado: (2026)

Learning and Leveraging World Models in Visual Representation Learning
por: Garrido, Quentin, et al.
Publicado: (2024)

Whole-Body Conditioned Egocentric Video Prediction
por: Bai, Yutong, et al.
Publicado: (2025)

Hierarchical World Models as Visual Whole-Body Humanoid Controllers
por: Hansen, Nicklas, et al.
Publicado: (2024)

Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
por: Moutakanni, Théo, et al.
Publicado: (2024)

PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
por: Arbel, Michael, et al.
Publicado: (2026)