{"total":15,"rows":[{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871,"area":null},{"id":"2406.05629","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","created":"2024-06-09","cited_by_count":17,"area":null},{"id":"2602.22394","title":"Vision Transformers Need More Than Registers","created":"2026-02-25","cited_by_count":15,"area":null},{"id":"2506.10178","title":"Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2505.05892","title":"Register and [CLS] tokens yield a decoupling of local and global features in large ViTs","created":"2025-05-09","cited_by_count":9,"area":null},{"id":"2407.02182","title":"Occlusion-Aware Seamless Segmentation","created":"2024-07-02","cited_by_count":7,"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":"2412.03215","title":"Beyond [cls]: Exploring the true potential of Masked Image Modeling representations","created":"2024-12-04","cited_by_count":6,"area":null},{"id":"2503.21772","title":"LOCORE: Image Re-ranking with Long-Context Sequence Modeling","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2402.15172","title":"Attention-Guided Masked Autoencoders For Learning Image Representations","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2404.01524","title":"On Train-Test Class Overlap and Detection for Image Retrieval","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2504.06738","title":"EDIT: Enhancing Vision Transformers by Mitigating Attention Sink through an Encoder-Decoder Architecture","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2506.08915","title":"Two-stage Vision Transformers and Hard Masking offer Robust Object Representations","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2602.12696","title":"Channel-Aware Probing for Multi-Channel Imaging","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.12021","title":"What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization","created":"2026-05-12","cited_by_count":0,"area":null}],"next_cursor":null}