{"total":117,"rows":[{"id":"2605.00078","title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","created":"2026-04-30","cited_by_count":75,"area":"wm"},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2605.00080","title":"World Model for Robot Learning: A Comprehensive Survey","created":"2026-04-30","cited_by_count":46,"area":"wm"},{"id":"2605.06388","title":"Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models","created":"2026-05-07","cited_by_count":22,"area":"wm"},{"id":"2606.15032","title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","created":"2026-06-13","cited_by_count":10,"area":"wm"},{"id":"2606.16533","title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","created":"2026-06-15","cited_by_count":9,"area":"wm"},{"id":"2608.06799","title":"Is Forward Prediction Enough? Physical State Grounding for JEPA World Models","created":"2026-08-07","cited_by_count":8,"area":"wm"},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2609.15478","title":"BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender","created":"2026-09-14","cited_by_count":6,"area":"diffusion"},{"id":"2609.16074","title":"World-Action Models for Robot Learning and Control: A Survey","created":"2026-09-13","cited_by_count":6,"area":"wm"},{"id":"2605.23993","title":"Nano World Models: A Minimalist Implementation of Future Video Prediction","created":"2026-05-17","cited_by_count":5,"area":"wm"},{"id":"2606.12195","title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","created":"2026-06-10","cited_by_count":5,"area":"agents"},{"id":"2608.19085","title":"DA-WAM: Decision-Aligned Future Latents for Driving World Models","created":"2026-08-19","cited_by_count":5,"area":"wm"},{"id":"2609.05588","title":"GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation","created":"2026-09-04","cited_by_count":5,"area":"wm"},{"id":"2605.07079","title":"Learning Visual Feature-Based World Models via Residual Latent Action","created":"2026-05-08","cited_by_count":4,"area":"wm"},{"id":"2607.13681","title":"Towards Spatial Supersensing in the Wild","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2605.01694","title":"Latent State Design for World Models under Sufficiency Constraints","created":"2026-05-03","cited_by_count":3,"area":"wm"},{"id":"2605.15477","title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","created":"2026-05-14","cited_by_count":3,"area":"wm"},{"id":"2605.15618","title":"Latent Video Prediction Learns Better World Models","created":"2026-05-15","cited_by_count":3,"area":"wm"},{"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":"2604.26182","title":"Lifting Embodied World Models for Planning and Control","created":"2026-04-28","cited_by_count":2,"area":"wm"},{"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":"2605.27734","title":"Learn from your own latents and not from tokens: A sample-complexity theory","created":"2026-05-26","cited_by_count":2,"area":"diffusion"},{"id":"2606.03180","title":"GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations","created":"2026-06-02","cited_by_count":2,"area":"mllm"},{"id":"2606.06219","title":"CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving","created":"2026-06-04","cited_by_count":2,"area":"driving"},{"id":"2608.29904","title":"Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model","created":"2026-08-30","cited_by_count":2,"area":"wm"},{"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":"2607.03558","title":"Latent Clarity: Bridging World-Model Kinematics to Semantic Manifolds for Video Anomaly Anticipation","created":"2026-07-03","cited_by_count":1,"area":"wm"},{"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":"2607.26196","title":"Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography","created":"2026-07-28","cited_by_count":1,"area":"ssm"},{"id":"2609.16697","title":"World Models for Embodied Intelligence: From Plausible to Controllable to Actionable","created":"2026-09-15","cited_by_count":1,"area":"wm"},{"id":"2609.23881","title":"MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space","created":"2026-09-20","cited_by_count":1,"area":"wm"},{"id":"2609.38163","title":"Rethinking Representations for World-Action Modeling","created":"2026-09-29","cited_by_count":1,"area":"wm"},{"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":"2605.07800","title":"SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models","created":"2026-05-08","cited_by_count":0,"area":"diffusion"},{"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":"2606.01095","title":"Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLA","created":"2026-05-31","cited_by_count":0,"area":"wm"},{"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":"2606.26969","title":"Einstein World Models","created":"2026-06-25","cited_by_count":0,"area":"wm"},{"id":"2606.27317","title":"OctoSense: Self-Supervised Learning for Multimodal Robot Perception","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.28712","title":"J-LAW: Joint Localization and Action-Conditioned World Modeling via Coupled Latent Factor Graphs","created":"2026-06-27","cited_by_count":0,"area":"wm"},{"id":"2607.02604","title":"DynaWM: A Base-VLA-Guided World Foundation Model for Moving-Object Manipulation","created":"2026-07-01","cited_by_count":0,"area":"vla"},{"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":"2608.06994","title":"Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models","created":"2026-08-07","cited_by_count":0,"area":"wm"},{"id":"2608.09771","title":"SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation","created":"2026-08-10","cited_by_count":0,"area":"wm"},{"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":"2608.28216","title":"WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes","created":"2026-08-28","cited_by_count":0,"area":"wm"},{"id":"2608.30378","title":"PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies","created":"2026-08-31","cited_by_count":0,"area":"vla"},{"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":"2609.10506","title":"DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation","created":"2026-09-09","cited_by_count":0,"area":"wm"},{"id":"2609.13507","title":"Pretraining for Sample-Efficient Neural Interfaces","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.18462","title":"CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models","created":"2026-09-16","cited_by_count":0,"area":"wm"},{"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":"2609.20277","title":"JEPA-WAM: Connecting Generated Visual Instructions to World Action Models through JEPA Latent Representations","created":"2026-08-04","cited_by_count":0,"area":"wm"},{"id":"2609.21379","title":"JEPA Guided Diffusion: Predictive Vision-Language Conditioning for Generative Traffic Forecasting","created":"2026-09-18","cited_by_count":0,"area":"diffusion"},{"id":"2609.24048","title":"What Matters in Designing World Action Models: An Empirical Study","created":"2026-09-21","cited_by_count":0,"area":"wm"},{"id":"2609.27455","title":"Latent evolving World Action Model","created":"2026-09-23","cited_by_count":0,"area":"wm"},{"id":"2609.28049","title":"Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings","created":"2026-09-23","cited_by_count":0,"area":"wm"},{"id":"2609.28923","title":"ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation","created":"2026-09-24","cited_by_count":0,"area":"diffusion"},{"id":"2609.29555","title":"Visual Representation and History Modeling for Navigation World Models","created":"2026-08-26","cited_by_count":0,"area":"wm"},{"id":"2609.31161","title":"I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2609.31349","title":"DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"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":"2609.34085","title":"AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.34362","title":"FutureDuet: Decoupling Observation Access from Future Supervision in World Action Models","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"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":"2609.36413","title":"One from Infinity: Actualizing Futures from Pretrained World Models into Robot Actions","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2609.36496","title":"Reimagine Video Dynamics","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37250","title":"V-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2609.39227","title":"Emergent Multi-View Geometry Through Self-Distillation","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2609.40037","title":"Enhancing Autoregressive Video Generation via Representation Adversarial Distillation","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}