Image de couverture de livre

Text-Conditional JEPA for Learning Semantically Rich Visual Representations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Chen, Li, Xianhang, Thilak, Vimal, Littwin, Etai, Susskind, Josh
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers
par: Li, Xianhang, et autres
Publié: (2025)

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning
par: Littwin, Etai, et autres
Publié: (2024)

How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
par: Littwin, Etai, et autres
Publié: (2024)

How PARTs assemble into wholes: Learning the relative composition of images
par: Ayoughi, Melika, et autres
Publié: (2025)

Vanishing Gradients in Reinforcement Finetuning of Language Models
par: Razin, Noam, et autres
Publié: (2023)

Learning Visual-Semantic Subspace Representations
par: Moreira, Gabriel, et autres
Publié: (2024)

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
par: Huang, Chen, et autres
Publié: (2024)

DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation
par: Gu, Jiatao, et autres
Publié: (2024)

Matryoshka Diffusion Models
par: Gu, Jiatao, et autres
Publié: (2023)

Normalizing Trajectory Models
par: Gu, Jiatao, et autres
Publié: (2026)

Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
par: Kuang, Yilun, et autres
Publié: (2026)

Improving GFlowNets for Text-to-Image Diffusion Alignment
par: Zhang, Dinghuai, et autres
Publié: (2024)

KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
par: Zimmermann, Eric, et autres
Publié: (2025)

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning
par: Kalibhat, Neha, et autres
Publié: (2024)

Unsqueeze [CLS] Bottleneck to Learn Rich Representations
par: Su, Qing, et autres
Publié: (2024)

Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methods
par: Alkhalefi, Mohammad, et autres
Publié: (2023)

Expressive Text-to-Image Generation with Rich Text
par: Ge, Songwei, et autres
Publié: (2023)

Semantic Concentration for Self-Supervised Dense Representations Learning
par: Wen, Peisong, et autres
Publié: (2025)

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
par: Maini, Pratyush, et autres
Publié: (2023)

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
par: Huang, Chen, et autres
Publié: (2025)

Mixed Autoencoder for Self-supervised Visual Representation Learning
par: Chen, Kai, et autres
Publié: (2023)

Semimage: HSV-Based Semantic Image Encoding for Disentangled Text Representation
par: Zare, Mohammad
Publié: (2025)

Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
par: Ren, Li, et autres
Publié: (2024)

ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning
par: Ye, Zihan, et autres
Publié: (2024)

BRo-JEPA: Learning Modular Arithmetic in Latent Space
par: Jha, Divyansh, et autres
Publié: (2026)

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
par: Berasi, Davide, et autres
Publié: (2025)

Learning Sparse Visual Representations via Spatial-Semantic Factorization
par: Zhao, Theodore Zhengde, et autres
Publié: (2026)

Unified Text-Image-to-Video Generation: A Training-Free Approach to Flexible Visual Conditioning
par: Lai, Bolin, et autres
Publié: (2025)

The Coupling Within: Flow Matching via Distilled Normalizing Flows
par: Berthelot, David, et autres
Publié: (2026)

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

Semantic Residual for Multimodal Unified Discrete Representation
par: Huang, Hai, et autres
Publié: (2024)

UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity
par: Fu, Yicheng, et autres
Publié: (2024)

Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness
par: Kim, Jaeill, et autres
Publié: (2024)

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
par: Gu, Jiatao, et autres
Publié: (2025)

Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
par: Li, Mengke, et autres
Publié: (2026)

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
par: Li, Siyuan, et autres
Publié: (2024)

SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
par: Miller, Luke James, et autres
Publié: (2026)

Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning
par: Cao, Ji, et autres
Publié: (2025)

Automated Learning of Semantic Embedding Representations for Diffusion Models
par: Jiang, Limai, et autres
Publié: (2025)

Visual Imitation Learning with Calibrated Contrastive Representation
par: Wang, Yunke, et autres
Publié: (2024)