Cover Image

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xianhang, Huang, Chen, Li, Chun-Liang, Malach, Eran, Susskind, Josh, Thilak, Vimal, Littwin, Etai
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Text-Conditional JEPA for Learning Semantically Rich Visual Representations
by: Huang, Chen, et al.
Published: (2026)

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning
by: Littwin, Etai, et al.
Published: (2024)

How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
by: Littwin, Etai, et al.
Published: (2024)

To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
by: Malach, Eran, et al.
Published: (2025)

Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
by: Wang, Linhan, et al.
Published: (2026)

Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
by: Zang, Yuhang, et al.
Published: (2024)

Steering Video Diffusion Transformers with Massive Activations
by: Cheng, Xianhang, et al.
Published: (2026)

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation
by: Liang, Renjie, et al.
Published: (2023)

How PARTs assemble into wholes: Learning the relative composition of images
by: Ayoughi, Melika, et al.
Published: (2025)

JEPA-VLA: Video Predictive Embedding is Needed for VLA Models
by: Miao, Shangchen, et al.
Published: (2026)

TAP-JEPA: Frozen Future-Latent Probing and Two-Stage Score Fusion for EPIC-KITCHENS-100 Action Anticipation
by: Wang, Chaoyang, et al.
Published: (2026)

Rethinking Reward Signals in Video GRPO: When Scores Become Targets
by: Li, Rui, et al.
Published: (2025)

Vanishing Gradients in Reinforcement Finetuning of Language Models
by: Razin, Noam, et al.
Published: (2023)

Learning Long-term Motion Embeddings for Efficient Kinematics Generation
by: Stracke, Nick, et al.
Published: (2026)

TIR-Flow: Active Video Search and Reasoning with Frozen VLMs
by: Jin, Hongbo, et al.
Published: (2026)

Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models
by: Orlova, Svetlana, et al.
Published: (2026)

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
by: Gui, Ming, et al.
Published: (2025)

Unmasked Teacher: Towards Training-Efficient Video Foundation Models
by: Li, Kunchang, et al.
Published: (2023)

Revisiting Adversarial Training at Scale
by: Wang, Zeyu, et al.
Published: (2024)

JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
by: Wan, Siheng, et al.
Published: (2025)

SSL: A Self-similarity Loss for Improving Generative Image Super-resolution
by: Chen, Du, et al.
Published: (2024)

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
by: Huang, Chen, et al.
Published: (2024)

What Happens Next? Next Scene Prediction with a Unified Video Model
by: Li, Xinjie, et al.
Published: (2025)

InstanceGen: Image Generation with Instance-level Instructions
by: Sella, Etai, et al.
Published: (2025)

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

Text-Guided Video Masked Autoencoder
by: Fan, David, et al.
Published: (2024)

Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure
by: Li, Zitong, et al.
Published: (2026)

Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended?
by: Liang, Chen, et al.
Published: (2024)

DiffSign: AI-Assisted Generation of Customizable Sign Language Videos With Enhanced Realism
by: Krishnamurthy, Sudha, et al.
Published: (2024)

FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition
by: Huang, Xiaohu, et al.
Published: (2024)

Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection
by: Cai, Zhaolin, et al.
Published: (2026)

Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives
by: Premi, Santosh
Published: (2026)

CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
by: Liu, Yanqing, et al.
Published: (2024)

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
by: Li, Xianhang, et al.
Published: (2025)

FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
by: Chen, Xi, et al.
Published: (2024)

Evaluation of deep learning architectures for wildlife object detection: A comparative study of ResNet and Inception
by: Amonga, Malach Obisa, et al.
Published: (2025)

HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detection
by: Hemmatyar, Mohammad Mahdi, et al.
Published: (2025)

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
by: Gu, Jiatao, et al.
Published: (2025)

PP-SSL : Priority-Perception Self-Supervised Learning for Fine-Grained Recognition
by: Li, ShuaiHeng, et al.
Published: (2024)

Matryoshka Diffusion Models
by: Gu, Jiatao, et al.
Published: (2023)