Cover Image

VISReg: Variance-Invariance-Sketching Regularization for JEPA training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Haiyu, Balestriero, Randall, Levine, Morgan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
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)

Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
by: Kuang, Yilun, et al.
Published: (2026)

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
by: Hsu, Chia-Hong, et al.
Published: (2026)

Beyond and Free from Diffusion: Invertible Guided Consistency Training
by: Hsu, Chia-Hong, et al.
Published: (2025)

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations
by: Bisulco, Anthony, et al.
Published: (2025)

Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps
by: Xia, Xue, et al.
Published: (2024)

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

Can the accuracy bias by facial hairstyle be reduced through balancing the training data?
by: Ozturk, Kagan, et al.
Published: (2024)

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

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

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

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

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
by: Humayun, Ahmed Imtiaz, et al.
Published: (2023)

Beyond [cls]: Exploring the true potential of Masked Image Modeling representations
by: Przewięźlikowski, Marcin, et al.
Published: (2024)

MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series
by: Xia, Xue, et al.
Published: (2025)

SketchTriplet: Self-Supervised Scenarized Sketch-Text-Image Triplet Generation
by: Wu, Zhenbei, et al.
Published: (2024)

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models
by: Ruan, Shouwei, et al.
Published: (2024)

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

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

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

Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation
by: Yang, Rui, et al.
Published: (2025)

Exploring parameter-efficient fine-tuning (PEFT) of billion-parameter vision models with QLoRA and DoRA: insights into generalization for limited-data image classification under a 98:1 test-to-train regime
by: Yang, Haiyu, et al.
Published: (2026)

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

UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
by: Le, Triet M.
Published: (2026)

AW-GATCN: Adaptive Weighted Graph Attention Convolutional Network for Event Camera Data Joint Denoising and Object Recognition
by: Li, Haiyu, et al.
Published: (2025)

VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
by: Chen, Delong, et al.
Published: (2025)

Discrete JEPA: Learning Discrete Token Representations without Reconstruction
by: Baek, Junyeob, et al.
Published: (2025)

DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture
by: He, Xiangteng, et al.
Published: (2025)

Shortcut Invariance: Targeted Jacobian Regularization in Disentangled Latent Space
by: Pal, Shivam, et al.
Published: (2025)

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

SketchAgent: Language-Driven Sequential Sketch Generation
by: Vinker, Yael, et al.
Published: (2024)

SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition
by: Tiwari, Adarsh, et al.
Published: (2024)

Social-JEPA: Emergent Geometric Isomorphism
by: Zhang, Haoran, et al.
Published: (2026)

JEPA for RL: Investigating Joint-Embedding Predictive Architectures for Reinforcement Learning
by: Kenneweg, Tristan, et al.
Published: (2025)

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

SketchingReality: From Freehand Scene Sketches To Photorealistic Images
by: Bourouis, Ahmed, et al.
Published: (2026)

Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch
by: Sain, Aneeshan, et al.
Published: (2025)

How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?
by: Koley, Subhadeep, et al.
Published: (2024)

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
by: Van Assel, Hugues, et al.
Published: (2025)

CustomSketching: Sketch Concept Extraction for Sketch-based Image Synthesis and Editing
by: Xiao, Chufeng, et al.
Published: (2024)