{"total":42,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64,"area":null},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44,"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":"2206.06501","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","created":"2022-06-13","cited_by_count":26,"area":null},{"id":"2302.04453","title":"Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning","created":"2023-02-09","cited_by_count":17,"area":null},{"id":"2405.14377","title":"CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization","created":"2024-05-23","cited_by_count":15,"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":"2104.07329","title":"All-You-Can-Fit 8-Bit Flexible Floating-Point Format for Accurate and Memory-Efficient Inference of Deep Neural Networks","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2303.02384","title":"Hierarchical Training of Deep Neural Networks Using Early Exiting","created":"2023-03-04","cited_by_count":5,"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":"2109.03513","title":"Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks","created":"2021-09-08","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":"2308.00890","title":"Tango: rethinking quantization for graph neural network training on GPUs","created":"2023-08-02","cited_by_count":4,"area":null},{"id":"2109.03991","title":"The challenge of reproducible ML: an empirical study on the impact of bugs","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2110.14904","title":"MERCURY: Accelerating DNN Training By Exploiting Input Similarity","created":"2021-10-28","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":"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":"2507.07149","title":"DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2510.22440","title":"Low-Precision Streaming PCA","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2401.08225","title":"Efficient and Mathematically Robust Operations for Certified Neural Networks Inference","created":"2024-01-16","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":"2103.15940","title":"Representation range needs for 16-bit neural network training","created":"2021-03-29","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":"2302.14458","title":"Ultra-low Precision Multiplication-free Training for Deep Neural Networks","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2305.10947","title":"Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2407.12637","title":"Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2506.21371","title":"MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2108.06626","title":"A Survey on GAN Acceleration Using Memory Compression Technique","created":"2021-08-14","cited_by_count":0,"area":null},{"id":"2205.08954","title":"One-way Explainability Isn't The Message","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2301.12809","title":"The Hidden Power of Pure 16-bit Floating-Point Neural Networks","created":"2023-01-30","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":"2504.11067","title":"Morphing-based Compression for Data-centric ML Pipelines","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2509.02538","title":"Federated learning over physical channels: adaptive algorithms with near-optimal guarantees","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2605.30728","title":"Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2610.17099","title":"LocalTrain: Integer-Only Local Learning for Energy-Efficient CNN Training on Edge FPGAs","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}