{"total":23,"rows":[{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2209.05735","title":"Learning ASR pathways: A sparse multilingual ASR model","created":"2022-09-13","cited_by_count":12,"area":null},{"id":"2406.09477","title":"Q-S5: Towards Quantized State Space Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2307.12659","title":"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization","created":"2023-07-24","cited_by_count":8,"area":null},{"id":"2205.03494","title":"Online Model Compression for Federated Learning with Large Models","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2501.03643","title":"Effective and Efficient Mixed Precision Quantization of Speech Foundation Models","created":"2025-01-07","cited_by_count":5,"area":null},{"id":"2210.09188","title":"Sub-8-bit quantization for on-device speech recognition: a regularization-free approach","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2303.08343","title":"Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models","created":"2023-03-15","cited_by_count":4,"area":null},{"id":"2310.02489","title":"ResidualTransformer: Residual Low-Rank Learning with Weight-Sharing for Transformer Layers","created":"2023-10-03","cited_by_count":4,"area":null},{"id":"2406.10160","title":"One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2406.19995","title":"Single Parent Family: A Spectrum of Family Members from a Single Pre-Trained Foundation Model","created":"2024-06-28","cited_by_count":3,"area":null},{"id":"2506.03515","title":"BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2309.09136","title":"Enhancing Quantised End-to-End ASR Models via Personalisation","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2406.00030","title":"Large Language Model Pruning","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2410.03294","title":"Resource-aware Mixed-precision Quantization for Enhancing Deployability of Transformers for Time-series Forecasting on Embedded FPGAs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2505.22608","title":"Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2604.10091","title":"SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2305.15536","title":"RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2408.10443","title":"Federated Learning of Large ASR Models in the Real World","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2601.02455","title":"Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2606.11836","title":"Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2610.13447","title":"O\\'ido: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}