{"total":54,"rows":[{"id":"2310.10537","title":"Microscaling Data Formats for Deep Learning","created":"2023-10-16","cited_by_count":152,"area":null},{"id":"2304.01089","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","created":"2023-04-03","cited_by_count":116,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"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":"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":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2105.03536","title":"Pareto-Optimal Quantized ResNet Is Mostly 4-bit","created":"2021-05-07","cited_by_count":26,"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":"2404.00928","title":"Instance-Aware Group Quantization for Vision Transformers","created":"2024-04-01","cited_by_count":25,"area":null},{"id":"2506.08027","title":"Recipes for Pre-training LLMs with MXFP8","created":"2025-05-30","cited_by_count":22,"area":null},{"id":"2304.04759","title":"Similarity search in the blink of an eye with compressed indices","created":"2023-04-07","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":"2405.03103","title":"Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2411.11745","title":"BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2511.06767","title":"QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations","created":"2025-11-10","cited_by_count":11,"area":null},{"id":"2211.02854","title":"Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2504.14152","title":"FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference","created":"2025-04-19","cited_by_count":9,"area":null},{"id":"2310.05079","title":"Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?","created":"2023-10-08","cited_by_count":8,"area":null},{"id":"2601.19026","title":"Is Finer Better? The Limits of Microscaling Formats in Large Language Models","created":"2026-01-26","cited_by_count":8,"area":null},{"id":"2601.19213","title":"M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2501.04052","title":"RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping","created":"2025-01-06","cited_by_count":7,"area":null},{"id":"2502.05376","title":"LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2110.14007","title":"TOD: GPU-accelerated Outlier Detection via Tensor Operations","created":"2021-10-26","cited_by_count":6,"area":null},{"id":"2407.01054","title":"Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2412.10059","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2507.04610","title":"any4: Learned 4-bit Numeric Representation for LLMs","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2206.07741","title":"Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2210.16621","title":"Empirical Evaluation of Post-Training Quantization Methods for Language Tasks","created":"2022-10-29","cited_by_count":4,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2311.09775","title":"MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2402.17985","title":"FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2404.00103","title":"PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2406.13868","title":"SDQ: Sparse Decomposed Quantization for LLM Inference","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2501.13331","title":"Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2603.28765","title":"Adaptive Block-Scaled Data Types","created":"2026-03-30","cited_by_count":4,"area":null},{"id":"2409.09245","title":"Robust Training of Neural Networks at Arbitrary Precision and Sparsity","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2411.06360","title":"An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2210.05470","title":"Block Format Error Bounds and Optimal Block Size Selection","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2305.05888","title":"Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks","created":"2023-05-10","cited_by_count":2,"area":null},{"id":"2410.06722","title":"Scaling Laws For Mixed Quantization","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2307.03712","title":"INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision Transformers","created":"2023-07-07","cited_by_count":1,"area":null},{"id":"2507.13970","title":"A Segmented Robot Grasping Perception Neural Network for Edge AI","created":"2025-07-18","cited_by_count":1,"area":null},{"id":"2512.12930","title":"SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2111.06457","title":"Variability-Aware Training and Self-Tuning of Highly Quantized DNNs for Analog PIM","created":"2021-11-11","cited_by_count":0,"area":null},{"id":"2309.16783","title":"Photonic Accelerators for Image Segmentation in Autonomous Driving and Defect Detection","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2407.01475","title":"Exploring FPGA designs for MX and beyond","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2409.18772","title":"A method of using RSVD in residual calculation of LowBit GEMM","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2507.09010","title":"Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2508.21493","title":"SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2603.13180","title":"MXNorm: Reusing MXFP block scales for efficient tensor normalisation","created":"2026-03-13","cited_by_count":0,"area":null}],"next_cursor":null}