Imagen de Portada

Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Premi, Santosh
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs
por: Adhikari, Santosh Premi, et al.
Publicado: (2026)

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers
por: Li, Xianhang, et al.
Publicado: (2025)

BRo-JEPA: Learning Modular Arithmetic in Latent Space
por: Jha, Divyansh, et al.
Publicado: (2026)

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

KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
por: Zimmermann, Eric, et al.
Publicado: (2025)

DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles
por: Daniel, Tal, et al.
Publicado: (2023)

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

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
por: Assran, Mido, et al.
Publicado: (2025)

From Image to Video: An Empirical Study of Diffusion Representations
por: Vélez, Pedro, et al.
Publicado: (2025)

CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities
por: Patapati, Santosh
Publicado: (2025)

Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation
por: Maduabuchi, Chika, et al.
Publicado: (2025)

Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection
por: Shiku, Kaito, et al.
Publicado: (2025)

Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
por: Park, Sol, et al.
Publicado: (2026)

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning
por: Lin, Han, et al.
Publicado: (2024)

An Empirical Study of World Model Quantization
por: Fu, Zhongqian, et al.
Publicado: (2026)

Contrastive Learning with Auxiliary User Detection for Identifying Activities
por: Ge, Wen, et al.
Publicado: (2024)

LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations
por: Varshney, Payal, et al.
Publicado: (2025)

Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition
por: Vellenga, Koen, et al.
Publicado: (2025)

US-JEPA: A Joint Embedding Predictive Architecture for Medical Ultrasound
por: Radhachandran, Ashwath, et al.
Publicado: (2026)

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

seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
por: Ghaemi, Hafez, et al.
Publicado: (2025)

VideoOrion: Tokenizing Object Dynamics in Videos
por: Feng, Yicheng, et al.
Publicado: (2024)

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
por: Yu, Sihyun, et al.
Publicado: (2025)

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
por: Yu, Sihyun, et al.
Publicado: (2024)

Memorization in 3D Shape Generation: An Empirical Study
por: Pu, Shu, et al.
Publicado: (2025)

Classes Are Not Equal: An Empirical Study on Image Recognition Fairness
por: Cui, Jiequan, et al.
Publicado: (2024)

Online Monitoring Framework for Automotive Time Series Data using JEPA Embeddings
por: Fertig, Alexander, et al.
Publicado: (2026)

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

Latent Geometry of Taste: Scalable Low-Rank Matrix Factorization for Recommender Systems
por: Salako, Joshua
Publicado: (2026)

Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
por: Yang, Penghui, et al.
Publicado: (2024)

LLVD: LSTM-based Explicit Motion Modeling in Latent Space for Blind Video Denoising
por: Rashid, Loay, et al.
Publicado: (2025)

Diagnostic Benchmarks for Invariant Learning Dynamics: Empirical Validation of the Eidos Architecture
por: Anderson, Datorien L.
Publicado: (2026)

An Empirical Study Into What Matters for Calibrating Vision-Language Models
por: Tu, Weijie, et al.
Publicado: (2024)

Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics
por: Hoang, Christopher, et al.
Publicado: (2025)

HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation
por: Li, Lihuan, et al.
Publicado: (2025)

Latent Action Pretraining from Videos
por: Ye, Seonghyeon, et al.
Publicado: (2024)

Enhancing Vector Quantization with Distributional Matching: A Theoretical and Empirical Study
por: Fang, Xianghong, et al.
Publicado: (2025)

Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution
por: Liu, Hua, et al.
Publicado: (2026)

An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning
por: Ghofrani, Fatemeh, et al.
Publicado: (2025)

Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images
por: Zhu, Aiqing, et al.
Publicado: (2025)