{"total":49,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"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":"2505.11594","title":"SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training","created":"2025-05-16","cited_by_count":66,"area":null},{"id":"2104.14129","title":"ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training","created":"2021-04-29","cited_by_count":61,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33,"area":null},{"id":"2206.11357","title":"GACT: Activation Compressed Training for Generic Network Architectures","created":"2022-06-22","cited_by_count":31,"area":null},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"area":null},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2502.20853","title":"Oscillation-Reduced MXFP4 Training for Vision Transformers","created":"2025-02-28","cited_by_count":21,"area":null},{"id":"2503.08040","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","created":"2025-03-11","cited_by_count":14,"area":null},{"id":"2510.27527","title":"TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control","created":"2025-10-31","cited_by_count":14,"area":null},{"id":"2301.00330","title":"Efficient On-device Training via Gradient Filtering","created":"2023-01-01","cited_by_count":13,"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":"2306.01381","title":"Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2309.15275","title":"Efficient Low-rank Backpropagation for Vision Transformer Adaptation","created":"2023-09-26","cited_by_count":10,"area":null},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2310.04467","title":"Design Principles for Lifelong Learning AI Accelerators","created":"2023-10-05","cited_by_count":9,"area":null},{"id":"2302.00232","title":"SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2501.14663","title":"End-to-end workflow for machine learning-based qubit readout with QICK and hls4ml","created":"2025-01-24","cited_by_count":8,"area":null},{"id":"2603.02170","title":"SageBwd: A Trainable Low-bit Attention","created":"2026-03-02","cited_by_count":8,"area":null},{"id":"2105.04246","title":"In-Hindsight Quantization Range Estimation for Quantized Training","created":"2021-05-10","cited_by_count":7,"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":"2207.09682","title":"Quantized Training of Gradient Boosting Decision Trees","created":"2022-07-20","cited_by_count":6,"area":null},{"id":"2212.08663","title":"Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2411.05873","title":"Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2206.08869","title":"Fast Lossless Neural Compression with Integer-Only Discrete Flows","created":"2022-06-17","cited_by_count":4,"area":null},{"id":"2208.04187","title":"DIVISION: Memory Efficient Training via Dual Activation Precision","created":"2022-08-05","cited_by_count":4,"area":null},{"id":"2102.13565","title":"Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision","created":"2021-02-26","cited_by_count":3,"area":null},{"id":"2310.03675","title":"Hadamard Domain Training with Integers for Class Incremental Quantized Learning","created":"2023-10-05","cited_by_count":3,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2408.14267","title":"1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2211.03741","title":"AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2304.06745","title":"End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2311.07427","title":"Boolean Variation and Boolean Logic BackPropagation","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2406.08830","title":"Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2406.15102","title":"HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization","created":"2024-06-21","cited_by_count":2,"area":null},{"id":"2411.10948","title":"Towards Accurate and Efficient Sub-8-Bit Integer Training","created":"2024-11-17","cited_by_count":2,"area":null},{"id":"2503.21261","title":"HOT: Hadamard-based Optimized Training","created":"2025-03-27","cited_by_count":2,"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":"2501.09849","title":"Coded Deep Learning: Framework and Algorithm","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2503.08719","title":"QuantU-Net: Efficient Wearable Medical Imaging Using Bitwidth as a Trainable Parameter","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2511.00874","title":"Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2601.03270","title":"Advances and Challenges in Semantic Textual Similarity: A Comprehensive Survey","created":"2025-12-19","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":"2607.14293","title":"Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2609.11716","title":"Why Does Post-Training Quantization Work?","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2412.12351","title":"Krony-PT: GPT2 compressed with Kronecker Products","created":"2024-12-16","cited_by_count":0,"area":null}],"next_cursor":null}