{"total":17,"rows":[{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2407.04490","title":"Micro-gesture Online Recognition using Learnable Query Points","created":"2024-07-05","cited_by_count":18,"area":null},{"id":"2409.18828","title":"MECG-E: Mamba-based ECG Enhancer for Baseline Wander Removal","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2501.13884","title":"Exploring Finetuned Audio-LLM on Heart Murmur Features","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2410.06285","title":"Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2411.15685","title":"State-Space Large Audio Language Models","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2409.09647","title":"Self-supervised Learning for Acoustic Few-Shot Classification","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2411.18902","title":"MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient Network","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2602.20981","title":"Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2412.08595","title":"Numerical Analysis of HiPPO-LegS ODE for Deep State Space Models","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2505.16911","title":"Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.10311","title":"Recognizing Dementia from Neuropsychological Tests with State Space Models","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2510.10948","title":"Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.20853","title":"Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2605.14014","title":"Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.14474","title":"Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026","created":"2026-07-16","cited_by_count":0,"area":null}],"next_cursor":null}