{"total":40,"rows":[{"id":"2310.10537","title":"Microscaling Data Formats for Deep Learning","created":"2023-10-16","cited_by_count":152,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41,"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":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"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":"2410.06040","title":"QERA: an Analytical Framework for Quantization Error Reconstruction","created":"2024-10-08","cited_by_count":22,"area":null},{"id":"2312.14972","title":"Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production","created":"2023-12-20","cited_by_count":21,"area":null},{"id":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20,"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":"2510.25602","title":"INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats","created":"2025-10-29","cited_by_count":18,"area":null},{"id":"2505.18659","title":"Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","cited_by_count":11,"area":null},{"id":"2312.05417","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","created":"2023-12-09","cited_by_count":8,"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":"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":"2407.04272","title":"Accelerating Communication in Deep Learning Recommendation Model Training with Dual-Level Adaptive Lossy Compression","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2406.13868","title":"SDQ: Sparse Decomposed Quantization for LLM Inference","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2409.05227","title":"BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration","created":"2024-09-08","cited_by_count":3,"area":null},{"id":"2511.06838","title":"P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2410.06722","title":"Scaling Laws For Mixed Quantization","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2506.17768","title":"Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2511.05811","title":"MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2609.02846","title":"UE5M3 FP4 Block Scaling for Stable Language Model Pretraining","created":"2026-09-02","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":"2410.11203","title":"Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2506.02077","title":"Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2512.09202","title":"Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2602.15563","title":"1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2410.10553","title":"SLaNC: Static LayerNorm Calibration","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2602.12962","title":"TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.19195","title":"The Thermodynamic Costs of Simple Linear Regression","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2608.03867","title":"Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.28358","title":"MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.00053","title":"Format-Aware Fusion for Fast FP4 Pretraining","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}