{"total":33,"rows":[{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2310.10537","title":"Microscaling Data Formats for Deep Learning","created":"2023-10-16","cited_by_count":152,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2302.08007","title":"With Shared Microexponents, A Little Shifting Goes a Long Way","created":"2023-02-16","cited_by_count":50,"area":null},{"id":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41,"area":null},{"id":"2110.15456","title":"FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding","created":"2021-10-28","cited_by_count":31,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2411.09909","title":"AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference","created":"2024-11-15","cited_by_count":19,"area":null},{"id":"2207.08822","title":"Is Integer Arithmetic Enough for Deep Learning Training?","created":"2022-07-18","cited_by_count":12,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2203.06673","title":"FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support","created":"2022-03-13","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2403.14353","title":"DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2303.05295","title":"Dynamic Stashing Quantization for Efficient Transformer Training","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2305.17190","title":"Multiplication-Free Transformer Training via Piecewise Affine Operations","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2101.11748","title":"Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2205.06287","title":"Adaptive Block Floating-Point for Analog Deep Learning Hardware","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2307.05035","title":"Number Systems for Deep Neural Network Architectures: A Survey","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2211.10737","title":"Accuracy Booster: Enabling 4-bit Fixed-point Arithmetic for DNN Training","created":"2022-11-19","cited_by_count":3,"area":null},{"id":"2411.03697","title":"TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2501.06066","title":"Distilling Calibration via Conformalized Credal Inference","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2605.12464","title":"Search Your Block Floating Point Scales!","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2301.13464","title":"Training with Mixed-Precision Floating-Point Assignments","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2311.17323","title":"Mirage: An RNS-Based Photonic Accelerator for DNN Training","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2102.02705","title":"EFloat: Entropy-coded Floating Point Format for Compressing Vector Embedding Models","created":"2021-02-04","cited_by_count":1,"area":null},{"id":"2204.10943","title":"FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems","created":"2022-04-22","cited_by_count":1,"area":null},{"id":"2204.13666","title":"Schr\\\"odinger's FP: Dynamic Adaptation of Floating-Point Containers for Deep Learning Training","created":"2022-04-28","cited_by_count":1,"area":null},{"id":"2409.17093","title":"BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2210.08951","title":"Approximating Continuous Convolutions for Deep Network Compression","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2211.02686","title":"LightNorm: Area and Energy-Efficient Batch Normalization Hardware for On-Device DNN Training","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2608.10010","title":"CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}