Cover Image

Intuitive physics understanding emerges from self-supervised pretraining on natural videos

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Garrido, Quentin, Ballas, Nicolas, Assran, Mahmoud, Bardes, Adrien, Najman, Laurent, Rabbat, Michael, Dupoux, Emmanuel, LeCun, Yann
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
by: Mur-Labadia, Lorenzo, et al.
Published: (2026)

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

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

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

IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
by: Bordes, Florian, et al.
Published: (2025)

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

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

PooDLe: Pooled and dense self-supervised learning from naturalistic videos
by: Wang, Alex N., et al.
Published: (2024)

Stochastic positional embeddings improve masked image modeling
by: Bar, Amir, et al.
Published: (2023)

A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
by: Krojer, Benno, et al.
Published: (2025)

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

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

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

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

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

Scaling Language-Free Visual Representation Learning
by: Fan, David, et al.
Published: (2025)

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
by: Mialon, Grégoire, et al.
Published: (2023)

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

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

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

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

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

Value-guided action planning with JEPA world models
by: Destrade, Matthieu, et al.
Published: (2025)

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

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

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

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

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

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

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

Light-weight probing of unsupervised representations for Reinforcement Learning
by: Zhang, Wancong, et al.
Published: (2022)

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

Modeling Caption Diversity in Contrastive Vision-Language Pretraining
by: Lavoie, Samuel, et al.
Published: (2024)

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
by: He, Xiaoxin, et al.
Published: (2023)

AI Must Embrace Specialization via Superhuman Adaptable Intelligence
by: Goldfeder, Judah, et al.
Published: (2026)

The Entropy Enigma: Success and Failure of Entropy Minimization
by: Press, Ori, et al.
Published: (2024)

RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training
by: Goswami, Raktim Gautam, et al.
Published: (2024)

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