{"total":68,"rows":[{"id":"2601.20540","title":"Advancing Open-source World Models","created":"2026-01-28","cited_by_count":154,"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":"2604.02029","title":"The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook","created":"2026-04-02","cited_by_count":43,"area":null},{"id":"2602.01166","title":"Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models","created":"2026-02-01","cited_by_count":22,"area":"lr"},{"id":"2601.14354","title":"VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models","created":"2026-01-20","cited_by_count":17,"area":"wm"},{"id":"2603.21389","title":"Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models","created":"2026-03-22","cited_by_count":15,"area":null},{"id":"2604.22748","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","created":"2026-04-24","cited_by_count":14,"area":"wm"},{"id":"2603.22281","title":"ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model","created":"2026-03-23","cited_by_count":13,"area":"wm"},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2603.19235","title":"Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding","created":"2026-03-19","cited_by_count":7,"area":"lr"},{"id":"2605.00933","title":"CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining","created":"2026-05-01","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2606.27014","title":"A Generalization Theory for JEPA-Based World Models","created":"2026-06-25","cited_by_count":5,"area":"wm"},{"id":"2602.20659","title":"Recursive Belief Vision Language Action Models","created":"2026-02-24","cited_by_count":4,"area":"vla"},{"id":"2603.16281","title":"Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2604.08065","title":"Multimodal Latent Reasoning via Predictive Embeddings","created":"2026-04-09","cited_by_count":4,"area":"lr"},{"id":"2605.05586","title":"AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2605.14759","title":"Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2608.20430","title":"RISE: Adaptive Imagination for World Action Models","created":"2026-08-20","cited_by_count":4,"area":"wm"},{"id":"2601.22128","title":"The Patient is not a Moving Document: A World Model Training Paradigm for Longitudinal EHR","created":"2026-01-29","cited_by_count":3,"area":"wm"},{"id":"2603.15553","title":"Self-Distillation of Hidden Layers for Self-Supervised Representation Learning","created":"2026-03-16","cited_by_count":3,"area":"distill"},{"id":"2605.14171","title":"CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.00133","title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2603.26799","title":"Gaussian Joint Embeddings For Self-Supervised Representation Learning","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2604.13518","title":"From Alignment to Prediction: A Study of Self-Supervised Learning and Predictive Representation Learning","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2605.10840","title":"Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories","created":"2026-05-11","cited_by_count":2,"area":"wm"},{"id":"2607.00784","title":"LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives","created":"2026-07-01","cited_by_count":2,"area":"mllm"},{"id":"2602.10461","title":"Unlocked Backpropagation using Wave Scattering","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.06999","title":"TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2603.12772","title":"PVI: Plug-in Visual Injection for Vision-Language-Action Models","created":"2026-03-13","cited_by_count":1,"area":"vla"},{"id":"2605.07568","title":"Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs","created":"2026-05-08","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":"2607.00889","title":"DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors","created":"2026-07-01","cited_by_count":1,"area":"wm"},{"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":"2607.18412","title":"Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2608.15869","title":"Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2608.28787","title":"Beyond Representation Learning: A Systematic Study of Joint-Embedding Predictive Generation for 3D Brain MRI","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2602.23588","title":"Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.01506","title":"OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder","created":"2026-05-02","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":"2605.31068","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":"2606.03837","title":"Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.10572","title":"One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA","created":"2026-06-09","cited_by_count":0,"area":"mllm"},{"id":"2606.21097","title":"GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.21358","title":"LEViL: Label-Efficient Video Learning via Zero-Shot Distillation over VLM-Generated Pseudo-Label Spaces","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.22870","title":"VideoLatent: Video-Language Learning via Latent Self-Forcing","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"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":"2607.02707","title":"VLRC: Vision-Language Reprojection Consistency as a scalable signal for better feed-forward 3D pretraining","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.07127","title":"Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories","created":"2026-07-08","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":"2608.06659","title":"CellWorld: From Gene-Level Reconstruction to Latent Cell Prediction in Spatial Transcriptomics Foundation Models","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.07214","title":"Toward a Causal Data Management Ecosystem for Decision Making and Agentic AI","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.09876","title":"Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning","created":"2026-08-10","cited_by_count":0,"area":"wm"},{"id":"2608.12748","title":"Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13495","title":"TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.01308","title":"CMRVision: A Foundation Model for Cardiac MR Image Analysis","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03572","title":"Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving","created":"2026-09-03","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":"2609.19483","title":"SCOUT: Sim-to-Real Text-Based Person Retrieval by Embedding-Space Prediction over Frozen Video Features","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.22674","title":"Mask-Aware Execution for Efficient JEPA Training","created":"2026-09-19","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":"2609.33148","title":"DroneWAM: Efficient World Action Model for Drone Visual Navigation","created":"2026-09-27","cited_by_count":0,"area":"wm"},{"id":"2609.36305","title":"Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.36952","title":"ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39727","title":"OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.05240","title":"Pythia: Toward Foundation World Models for Multimodal Time Series","created":"2026-10-04","cited_by_count":0,"area":"wm"},{"id":"2610.14324","title":"EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19683","title":"Enhancing Latent World Models with Associative Memory","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}