{"total":30,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105,"area":null},{"id":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"area":null},{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2108.02297","title":"Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsity","created":"2021-08-04","cited_by_count":20,"area":null},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2206.12372","title":"QReg: On Regularization Effects of Quantization","created":"2022-06-24","cited_by_count":11,"area":null},{"id":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2510.10467","title":"AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2108.12074","title":"4-bit Quantization of LSTM-based Speech Recognition Models","created":"2021-08-27","cited_by_count":8,"area":null},{"id":"2404.11769","title":"QGen: On the Ability to Generalize in Quantization Aware Training","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2506.03781","title":"Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2111.14836","title":"Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2202.07462","title":"Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference","created":"2022-02-14","cited_by_count":2,"area":null},{"id":"2606.04050","title":"LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2105.01869","title":"Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression","created":"2021-05-05","cited_by_count":1,"area":null},{"id":"2402.04012","title":"Quantized Approximately Orthogonal Recurrent Neural Networks","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2105.01875","title":"Modulating Regularization Frequency for Efficient Compression-Aware Model Training","created":"2021-05-05","cited_by_count":0,"area":null},{"id":"2106.09886","title":"Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2211.12715","title":"Embedding Compression for Text Classification Using Dictionary Screening","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2502.00047","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2510.19482","title":"ELUTQ: Optimizing Quantization Accuracy under LUT-Based Computation for Edge LLMs","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2609.04490","title":"When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.38599","title":"JARQ: Joint Alternating Refinement for Quantization","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}