{"total":273,"rows":[{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2511.03773","title":"Scaling Agent Learning via Experience Synthesis","created":"2025-11-05","cited_by_count":44,"area":null},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30,"area":null},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2507.08800","title":"NeuralOS: Towards Simulating Operating Systems via Neural Generative Models","created":"2025-07-11","cited_by_count":19,"area":null},{"id":"2507.22229","title":"TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction","created":"2025-07-29","cited_by_count":19,"area":null},{"id":"2603.16195","title":"S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight","created":"2026-03-17","cited_by_count":17,"area":null},{"id":"2602.02603","title":"EchoJEPA: A Latent Predictive Foundation Model for Echocardiography","created":"2026-02-02","cited_by_count":13,"area":null},{"id":"2605.04326","title":"A foundation model of vision, audition, and language for in-silico neuroscience","created":"2026-05-05","cited_by_count":13,"area":null},{"id":"2509.24317","title":"Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2602.10102","title":"VideoWorld 2: Learning Transferable Knowledge from Real-world Videos","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2604.08503","title":"Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics","created":"2026-04-09","cited_by_count":12,"area":null},{"id":"2603.13227","title":"Representation Learning for Spatiotemporal Physical Systems","created":"2026-03-13","cited_by_count":11,"area":null},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2604.14816","title":"NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results","created":"2026-04-16","cited_by_count":10,"area":null},{"id":"2511.12940","title":"Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention","created":"2025-11-17","cited_by_count":9,"area":null},{"id":"2602.18742","title":"RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning","created":"2026-02-21","cited_by_count":8,"area":null},{"id":"2603.12267","title":"EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2509.19453","title":"The Platonic Universe: Do Foundation Models See the Same Sky?","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2511.19356","title":"Rethinking Reward Signals in Video GRPO: When Scores Become Targets","created":"2025-11-24","cited_by_count":6,"area":null},{"id":"2601.03665","title":"PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2605.28230","title":"Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation","created":"2026-05-27","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":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2511.02767","title":"Dynamic Reflections: Probing Video Representations with Text Alignment","created":"2025-11-04","cited_by_count":5,"area":null},{"id":"2511.17309","title":"MuM: Multi-View Masked Image Modeling for 3D Vision","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2601.05237","title":"ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2602.07064","title":"OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2606.15956","title":"You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences","created":"2026-06-14","cited_by_count":5,"area":null},{"id":"2606.17742","title":"BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics","created":"2026-06-16","cited_by_count":5,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2510.14876","title":"BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2510.21581","title":"Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2510.21840","title":"Improving the Physics of Video Generation with VJEPA-2 Reward Signal","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2512.02846","title":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","created":"2025-12-02","cited_by_count":4,"area":null},{"id":"2602.05638","title":"SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2603.00049","title":"BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"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":"2604.21681","title":"Sapiens2","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2605.03517","title":"Understanding Self-Supervised Learning via Latent Distribution Matching","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2606.14957","title":"Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2607.26811","title":"DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2507.17844","title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2509.25146","title":"Fast Feature Field ($\\text{F}^3$): A Predictive Representation of Events","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.03075","title":"What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives","created":"2025-10-03","cited_by_count":3,"area":null},{"id":"2510.19150","title":"X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2602.09146","title":"SemanticMoments: Training-Free Motion Similarity via Third Moment Features","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2602.17478","title":"QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2602.21668","title":"Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2602.22779","title":"TrajTok: Learning Trajectory Tokens enables better Video Understanding","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.00461","title":"ReMoT: Reinforcement Learning with Motion Contrast Triplets","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2604.01693","title":"From Understanding to Erasing: Towards Complete and Stable Video Object Removal","created":"2026-04-02","cited_by_count":3,"area":null},{"id":"2605.22809","title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.14813","title":"JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2606.19491","title":"Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2606.31946","title":"World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2607.11064","title":"WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation","created":"2026-07-13","cited_by_count":3,"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":"2507.23077","title":"A Foundation Model for Material Fracture Prediction","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2509.21595","title":"Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.05558","title":"Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.13714","title":"DeDelayed: Deleting Remote Inference Delay via On-Device Correction","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2511.09675","title":"PriVi: Towards A General-Purpose Video Model For Primate Behavior In The Wild","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2511.14918","title":"X-WIN: Building Chest Radiograph World Model via Predictive Sensing","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2601.05911","title":"Pantagruel: Unified Self-Supervised Encoders for French Text and Speech","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.04411","title":"Self-evolving Embodied AI","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2602.14705","title":"It's a Matter of Time: Three Lessons on Long-Term Motion for Perception","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2603.08648","title":"CAST: Modeling Visual State Transitions for Consistent Video Retrieval","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"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":"2605.03245","title":"Text-Conditional JEPA for Learning Semantically Rich Visual Representations","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2606.07770","title":"Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.14981","title":"Inference-time Policy Steering via Vision and Touch","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2606.25225","title":"MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2606.30068","title":"Predictive Objectives Discard Exogenous Control-Relevant Features: A Controlled Mechanistic Study","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2607.26694","title":"Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2506.21329","title":"Active Inference AI Systems for Scientific Discovery","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2509.18108","title":"Solve it with EASE","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2510.04006","title":"Learning more physically realistic dynamics in machine-learning based weather forecasting with latent-space constraints","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2512.10617","title":"Lang2Motion: Bridging Language and Motion through Joint Embedding Spaces","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2512.12432","title":"Data-driven modelling of autonomous and forced dynamical systems","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2601.14096","title":"Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.02381","title":"Self-Supervised Learning from Structural Invariance","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.04583","title":"PEPR: Privileged Event-based Predictive Regularization for Domain Generalization","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.10461","title":"Unlocked Backpropagation using Wave Scattering","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.14024","title":"EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models","created":"2026-02-15","cited_by_count":1,"area":null},{"id":"2602.14672","title":"MeFEm: Medical Face Embedding model","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.03564","title":"Modeling Cross-vision Synergy for Unified Large Vision Model","created":"2026-03-03","cited_by_count":1,"area":null}],"next_cursor":"100"}