Joint Embedding Predictive Architectures Focus on Slow Features

20 November 2022

Papers citing "Joint Embedding Predictive Architectures Focus on Slow Features"

7 / 7 papers shown

Title
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks Etai Littwin Omid Saremi Madhu Advani Vimal Thilak Preetum Nakkiran Chen Huang Joshua Susskind 37 3 0 03 Jul 2024
T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computation Lihuan Li Hao Xue Yang Song Flora Salim 39 1 0 13 Jun 2024
Hierarchical World Models as Visual Whole-Body Humanoid Controllers Nicklas Hansen V. JyothirS Vlad Sobal Yann LeCun Xiaolong Wang Hao Su VGen 48 10 0 28 May 2024
Towards Principled Representation Learning from Videos for Reinforcement Learning Dipendra Kumar Misra Akanksha Saran Tengyang Xie Alex Lamb John Langford SSL OffRL 34 5 0 20 Mar 2024
Gradient-based Planning with World Models V. JyothirS Siddhartha Jalagam Yann LeCun Vlad Sobal 24 4 0 28 Dec 2023
A Cookbook of Self-Supervised Learning Randall Balestriero Mark Ibrahim Vlad Sobal Ari S. Morcos Shashank Shekhar ... Pierre Fernandez Amir Bar Hamed Pirsiavash Yann LeCun Micah Goldblum SyDa FedML SSL 44 273 0 24 Apr 2023
Decoupling Representation Learning from Reinforcement Learning Adam Stooke Kimin Lee Pieter Abbeel Michael Laskin SSL DRL 280 339 0 14 Sep 2020