{"total":47,"rows":[{"id":"2605.15153","title":"Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action","created":"2026-05-14","cited_by_count":8,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2606.15956","title":"You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences","created":"2026-06-14","cited_by_count":5,"area":null},{"id":"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":"2608.19613","title":"What Matters for Latent Actions in Robot Learning","created":"2026-08-20","cited_by_count":4,"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":"2603.29496","title":"Metriplector: From Field Theory to Neural Architecture","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.03413","title":"Learning to Theorize the World from Observation","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":"2604.24662","title":"Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.09693","title":"Do multimodal models imagine electric sheep?","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2607.12547","title":"Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel","created":"2026-07-14","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":"2603.28750","title":"Immediate Derivatives Suffice for Online Recurrent Adaptation","created":"2026-03-30","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":"2605.07554","title":"ProteinJEPA: Latent prediction improves protein language model pretraining","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.07775","title":"DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT","created":"2026-06-05","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":"2606.29723","title":"ScaleAware-JEPA: Latent Representation for Discovery in Multiscale Physical Fields","created":"2026-06-29","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":"2607.17574","title":"Predictive Training with Latent Imagination for Visual Quadruped Navigation","created":"2026-07-20","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":"2607.21644","title":"Toward Goal-Agnostic Joint-Embedding Predictive Control of Partial Differential Equations","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.14355","title":"Disentangled Shared Representations Improve Morpho-Transcriptomic Integration","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.16457","title":"Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.19863","title":"Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.21147","title":"Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning","created":"2026-08-21","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":"2608.24093","title":"Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videos","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.04261","title":"Self-Supervised Pretraining of Molecular Graph Encoders with LeJEPA","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04325","title":"The microscope is the mask: privileged views and labels from a cryo-ET forward model","created":"2026-09-03","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":"2609.21221","title":"A Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.31868","title":"Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals","created":"2026-09-25","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":"2609.37392","title":"Learning Macroscopic Dynamics without Reconstructing Microscopic States","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37798","title":"GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38383","title":"Learning to Plan from Random Exploration","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00976","title":"Variational Streaming Flow: Probabilistic Forecasting in Physical Time","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02864","title":"NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03106","title":"S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05731","title":"T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representations","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.09457","title":"DSReg: Provably Recovering Individual World Latents without Reconstruction","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12172","title":"Unifying Policy Learning and State Prediction through Spatial Language Modeling","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12349","title":"SplitJEPA: Learning Invariant and Variant Latent Worlds without Reconstruction","created":"2026-10-08","cited_by_count":0,"area":null},{"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}],"next_cursor":null}