{"total":21,"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":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83,"area":null},{"id":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","cited_by_count":25,"area":null},{"id":"2205.09103","title":"Single-Shot Optical Neural Network","created":"2022-05-18","cited_by_count":12,"area":null},{"id":"2106.13914","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","created":"2021-06-26","cited_by_count":7,"area":null},{"id":"2403.05465","title":"Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference","created":"2024-03-08","cited_by_count":7,"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":"2307.05035","title":"Number Systems for Deep Neural Network Architectures: A Survey","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2102.09262","title":"PLAM: a Posit Logarithm-Approximate Multiplier","created":"2021-02-18","cited_by_count":3,"area":null},{"id":"2210.16556","title":"MinUn: Accurate ML Inference on Microcontrollers","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2105.00053","title":"PositNN: Training Deep Neural Networks with Mixed Low-Precision Posit","created":"2021-04-30","cited_by_count":2,"area":null},{"id":"2502.19734","title":"FPGA-Accelerated SpeckleNN with SNL for Real-time X-ray Single-Particle Imaging","created":"2025-02-27","cited_by_count":1,"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":"2302.01474","title":"Defensive ML: Defending Architectural Side-channels with Adversarial Obfuscation","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2309.07158","title":"Compressed Real Numbers for AI: a case-study using a RISC-V CPU","created":"2023-09-11","cited_by_count":0,"area":null},{"id":"2406.02579","title":"An Open-Source Framework for Efficient Numerically-Tailored Computations","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2407.15143","title":"Investigating Long-term Training for Remote Sensing Object Detection","created":"2024-07-21","cited_by_count":0,"area":null},{"id":"2602.14701","title":"Unbiased Approximate Vector-Jacobian Products for Efficient Backpropagation","created":"2026-02-16","cited_by_count":0,"area":null}],"next_cursor":null}