{"total":39,"rows":[{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2310.11028","title":"Matrix Compression via Randomized Low Rank and Low Precision Factorization","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23,"area":null},{"id":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","cited_by_count":19,"area":null},{"id":"2307.00526","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","created":"2023-07-02","cited_by_count":17,"area":null},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2205.10036","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","created":"2022-05-20","cited_by_count":15,"area":null},{"id":"2103.11367","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","created":"2021-03-21","cited_by_count":14,"area":null},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13,"area":null},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10,"area":null},{"id":"2205.04157","title":"Task-specific Compression for Multi-task Language Models using Attribution-based Pruning","created":"2022-05-09","cited_by_count":7,"area":null},{"id":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2304.05511","title":"Training Large Language Models Efficiently with Sparsity and Dataflow","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2206.14318","title":"Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2310.08797","title":"A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2106.08181","title":"Direction is what you need: Improving Word Embedding Compression in Large Language Models","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2203.09055","title":"Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT","created":"2022-03-17","cited_by_count":4,"area":null},{"id":"2203.13444","title":"Vision Transformer Compression with Structured Pruning and Low Rank Approximation","created":"2022-03-25","cited_by_count":4,"area":null},{"id":"2312.13211","title":"DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2511.11683","title":"Stratified Knowledge-Density Super-Network for Scalable Vision Transformers","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2206.15014","title":"Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding","created":"2022-06-30","cited_by_count":2,"area":null},{"id":"2302.11812","title":"Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers","created":"2023-02-23","cited_by_count":2,"area":null},{"id":"2306.01076","title":"Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2109.08449","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2302.04045","title":"Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2302.04443","title":"Enhancing E-Commerce Recommendation using Pre-Trained Language Model and Fine-Tuning","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2302.05323","title":"On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2310.07911","title":"Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2501.04211","title":"CURing Large Models: Compression via CUR Decomposition","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2109.08627","title":"Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2110.15802","title":"BERMo: What can BERT learn from ELMo?","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2310.03424","title":"Neural Language Model Pruning for Automatic Speech Recognition","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2403.17607","title":"Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2506.13514","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2508.00220","title":"Semantic Compression for Word and Sentence Embeddings using Discrete Wavelet Transform","created":"2025-07-31","cited_by_count":0,"area":null}],"next_cursor":null}