{"total":14,"rows":[{"id":"2506.08010","title":"Vision Transformers Don't Need Trained Registers","created":"2025-06-09","cited_by_count":41,"area":null},{"id":"2505.21501","title":"Vision Transformers with Self-Distilled Registers","created":"2025-05-27","cited_by_count":12,"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":"2506.15153","title":"SynPo: Boosting Training-Free Few-Shot Medical Segmentation via High-Quality Negative Prompts","created":"2025-06-18","cited_by_count":9,"area":null},{"id":"2510.09017","title":"Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2502.07004","title":"Demystifying Singular Defects in Large Language Models","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2511.05509","title":"Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2605.07821","title":"Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2511.05168","title":"Another BRIXEL in the Wall: Towards Cheaper Dense Features","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2604.00172","title":"Suppressing Non-Semantic Noise in Masked Image Modeling Representations","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.14433","title":"Zero-Ablation Overstates Register Content Dependence in DINO Vision Transformers","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.19622","title":"UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.09082","title":"REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}