{"total":13,"rows":[{"id":"2509.06888","title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","created":"2025-09-08","cited_by_count":45,"area":null},{"id":"2507.07814","title":"Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers","created":"2025-07-10","cited_by_count":11,"area":null},{"id":"2512.23065","title":"TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish","created":"2025-12-28","cited_by_count":1,"area":null},{"id":"2603.12191","title":"Long-Context Encoder Models for Polish Language Understanding","created":"2026-03-12","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":"2504.05112","title":"ABCDWaveNet: Advancing Robust Road Ponding Detection in Fog through Dynamic Frequency-Spatial Synergy","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2510.12285","title":"Chinese ModernBERT with Whole-Word Masking","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.12534","title":"ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2602.15814","title":"Avey-B","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2605.07622","title":"Is She Even Relevant? When BERT Ignores Explicit Gender Cues","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.22722","title":"moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2610.06513","title":"SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.15028","title":"UltraBERT: Beyond the Limit of BERT Pre-Training","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}