{"total":22,"rows":[{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2309.17224","title":"Training and inference of large language models using 8-bit floating point","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"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":"2312.12472","title":"A Performance Evaluation of a Quantized Large Language Model on Various Smartphones","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2604.15416","title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2301.03904","title":"RedMule: A Mixed-Precision Matrix-Matrix Operation Engine for Flexible and Energy-Efficient On-Chip Linear Algebra and TinyML Training Acceleration","created":"2023-01-10","cited_by_count":4,"area":null},{"id":"2311.12359","title":"Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2312.02210","title":"Low-Precision Mixed-Computation Models for Inference on Edge","created":"2023-12-03","cited_by_count":4,"area":null},{"id":"2407.17353","title":"Scalify: scale propagation for efficient low-precision LLM training","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2504.20634","title":"On Stochastic Rounding with Few Random Bits","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2507.10618","title":"Compute Requirements for Algorithmic Innovation in Frontier AI Models","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2311.05034","title":"Just-in-time Quantization with Processing-In-Memory for Efficient ML Training","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2505.12988","title":"Optimal Formats for Weight Quantisation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2602.02707","title":"Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2606.04028","title":"Novel Aspects of IEEE SA P3109 Arithmetic Formats for Machine Learning","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2511.06313","title":"Precision-Scalable Microscaling Datapaths with Optimized Reduction Tree for Efficient NPU Integration","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2606.09686","title":"Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.01653","title":"Hadamard-Domain Model Quantization for Learned Image Coding","created":"2026-08-03","cited_by_count":0,"area":null}],"next_cursor":null}