{"total":51,"rows":[{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2608.13556","title":"V-RAE: Rethinking Video Latent Spaces for Generation","created":"2026-08-13","cited_by_count":3,"area":null},{"id":"2608.27395","title":"LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2605.20901","title":"VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2605.20904","title":"JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2605.06809","title":"LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.15394","title":"Representation Without Reward: A JEPA Audit for LLM Fine-Tuning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.20388","title":"How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.00662","title":"TAP-JEPA: Frozen Future-Latent Probing and Two-Stage Score Fusion for EPIC-KITCHENS-100 Action Anticipation","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.00694","title":"FROST-STA: Frozen Dense Features for the Ego4D Short-Term Object Interaction Anticipation","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.25880","title":"USS: Unifying Spatial-Semantic Prompting for End to End Embodied Visual Tracking","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.32039","title":"GEAR: Guided End-to-End AutoRegression for Image Synthesis","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.14228","title":"SeeSE3: Emergence of 3D Space in Vision Features","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.21371","title":"DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2604.16503","title":"Motif-Video 2B: Technical Report","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.23670","title":"Preserve, Then Resolve: Many-to-Many Association and Robust Estimation with General-Purpose Visual Features","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.06487","title":"3D MRI Image Pretraining via Controllable 2D Slice Navigation Task","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.17165","title":"Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.20674","title":"Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.27304","title":"PlayClass: Automated Play Behaviour Classification in Poultry","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.31068","title":"HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.23256","title":"P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architecture","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.26410","title":"Neural Voxel Dynamics: Learning Volumetric Feature Advection for 3D Physics in V-JEPA Latent Space","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27317","title":"OctoSense: Self-Supervised Learning for Multimodal Robot Perception","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05250","title":"Streaming Neural Speech Codecs through Time-Invariant Representations","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.11998","title":"HPC-Enabled Video-based Coastal Wave Parameter Estimation Using V-JEPA and Deep Spatiotemporal Learning","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.16274","title":"The JEPA Predictor: A Transferable Operator for Occluded Feature Completion","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.19889","title":"Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.21576","title":"Self-Supervised Learning of Structured Dynamics from Videos","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.22351","title":"IQ-JEPA: A Joint-Embedding Predictive Architecture with a Hermitian Vision Transformer for Sound Speed and Attenuation Estimation from Ultrasound IQ Data","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.00976","title":"Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.05774","title":"SR-JEPA: Learning Predictive Latent State in 3D Scenes","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.21160","title":"Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.02471","title":"Learning to Track from Privileged Target Appearances","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.06823","title":"Generalist Open-World Temporal Perception","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.08636","title":"From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.13507","title":"Pretraining for Sample-Efficient Neural Interfaces","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.18562","title":"Sim-to-Real Traffic Scene Understanding by Decoupling Semantics from Caption Generation with V-JEPA","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.31665","title":"Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.33000","title":"TriDrive: Joint Driver, Vehicle, and Road Modeling for Forecasting and Driver Monitoring","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34715","title":"PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34733","title":"SurgGMF: Fully Causal Gaussian Motion Forecasting for Anticipatory Surgical Scene Rendering","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35341","title":"Generative Uncertainty as a Self-supervised Signal for Semantic Similarity Learning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35464","title":"W2Rep: Learning Visual Representations by Watching the World Change","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36496","title":"Reimagine Video Dynamics","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40037","title":"Enhancing Autoregressive Video Generation via Representation Adversarial Distillation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40129","title":"VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00003","title":"STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2610.03717","title":"Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.10013","title":"Scalable Patch-Level Self-Supervised Learning","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}