Cover Image

Why and How Auxiliary Tasks Improve JEPA Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Jiacan, Chen, Siyi, Liu, Mingrui, Horiuchi, Nono, Braverman, Vladimir, Xu, Zicheng, Haramati, Dan, Balestriero, Randall
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
by: Cai, Daniel, et al.
Published: (2025)

Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks
by: Patel, Niket, et al.
Published: (2025)

stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
by: Maes, Lucas, et al.
Published: (2026)

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

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
by: Ibrahim, Mark, et al.
Published: (2024)

Deep Networks Always Grok and Here is Why
by: Humayun, Ahmed Imtiaz, et al.
Published: (2024)

SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earth
by: Masi, Nick, et al.
Published: (2025)

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
by: Huang, Hai, et al.
Published: (2024)

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

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

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
by: Balestriero, Randall, et al.
Published: (2023)

The Fair Language Model Paradox
by: Pinto, Andrea, et al.
Published: (2024)

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

Next Token Perception Score: Analytical Assessment of your LLM Perception Skills
by: Cheng, Yu-Ang, et al.
Published: (2025)

PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning
by: Lu, Wenquan, et al.
Published: (2026)

UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
by: Zhang, Jianke, et al.
Published: (2025)

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
by: Otero, Daniel, et al.
Published: (2024)

Enhancing Recommendation with Denoising Auxiliary Task
by: Liu, Pengsheng, et al.
Published: (2024)

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
by: Reizinger, Patrik, et al.
Published: (2025)

Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation
by: Pourmirzaei, Mahdi, et al.
Published: (2021)

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
by: Zhang, Jiaqi, et al.
Published: (2025)

On the Geometry of Deep Learning
by: Balestriero, Randall, et al.
Published: (2024)

VISReg: Variance-Invariance-Sketching Regularization for JEPA training
by: Wu, Haiyu, et al.
Published: (2026)

SplInterp: Improving our Understanding and Training of Sparse Autoencoders
by: Budd, Jeremy, et al.
Published: (2025)

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation
by: Qi, Carl, et al.
Published: (2024)

Representation Learning of Auxiliary Concepts for Improved Student Modeling and Exercise Recommendation
by: Badran, Yahya, et al.
Published: (2025)

Language Models Benefit from Preparation with Elicited Knowledge
by: Yu, Jiacan, et al.
Published: (2024)

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
by: Li, Haoran, et al.
Published: (2025)

Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
by: Sengupta, Biswa
Published: (2026)

SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures
by: Hartman, Max, et al.
Published: (2025)

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
by: Xu, Zicheng, et al.
Published: (2025)

Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison
by: Lange, Moritz, et al.
Published: (2023)

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

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
by: Feizi, Aarash, et al.
Published: (2024)

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
by: Lu, Wenquan, et al.
Published: (2025)

Auxiliary Reward Generation with Transition Distance Representation Learning
by: Li, Siyuan, et al.
Published: (2024)

Towards Causal Representation Learning with Observable Sources as Auxiliaries
by: Kim, Kwonho, et al.
Published: (2025)

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning
by: Vujinovic, Aleksandar, et al.
Published: (2025)