{"total":15,"rows":[{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2507.06230","title":"Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion","created":"2025-07-08","cited_by_count":13,"area":null},{"id":"2512.15715","title":"In Pursuit of Pixel Supervision for Visual Pre-training","created":"2025-12-17","cited_by_count":13,"area":null},{"id":"2509.24901","title":"Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification","created":"2025-09-29","cited_by_count":7,"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":"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":"2510.23484","title":"T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2602.01905","title":"Learning Sparse Visual Representations via Spatial-Semantic Factorization","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2607.04011","title":"Separating Representation from Reconstruction Enables Scalable Text Encoders","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2503.14304","title":"RoMedFormer: A Rotary-Embedding Transformer Foundation Model for 3D Genito-Pelvic Structure Segmentation in MRI and CT","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2511.22281","title":"Collapse of Patches: Ranking Image Patches for Efficient Visual Modeling","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2602.05845","title":"Self-Supervised Learning with a Multi-Task Latent Space Objective","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.16305","title":"BAT: Better Audio Transformer Guided by Convex Gated Probing","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2607.00277","title":"AEGIS: A Multi-Task Joint-Embedding Predictive Architecture for Mammography","created":"2026-06-30","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}],"next_cursor":null}