{"list":"other","total":56,"rows":[{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169},{"id":"2310.10537","title":"Microscaling Data Formats for Deep Learning","created":"2023-10-16","cited_by_count":152},{"id":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125},{"id":"2304.01089","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","created":"2023-04-03","cited_by_count":116},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82},{"id":"2509.25149","title":"Pretraining Large Language Models with NVFP4","created":"2025-09-29","cited_by_count":76},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31},{"id":"2505.11695","title":"Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization","created":"2025-05-16","cited_by_count":28},{"id":"2502.02617","title":"PolarQuant: Quantizing KV Caches with Polar Transformation","created":"2025-02-04","cited_by_count":27},{"id":"2502.09720","title":"NestQuant: Nested Lattice Quantization for Matrix Products and LLMs","created":"2025-02-13","cited_by_count":23},{"id":"2411.17525","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","created":"2024-11-26","cited_by_count":21},{"id":"2601.22813","title":"Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation","created":"2026-01-30","cited_by_count":21},{"id":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20},{"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},{"id":"2406.09904","title":"QQQ: Quality Quattuor-Bit Quantization for Large Language Models","created":"2024-06-14","cited_by_count":16},{"id":"2508.04853","title":"Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos","created":"2025-08-06","cited_by_count":16},{"id":"2410.13780","title":"Optimal Quantization for Matrix Multiplication","created":"2024-10-17","cited_by_count":14},{"id":"2410.20650","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","created":"2024-10-28","cited_by_count":14},{"id":"2412.08832","title":"HadaCore: Tensor Core Accelerated Hadamard Transform Kernel","created":"2024-12-12","cited_by_count":12},{"id":"2508.03485","title":"LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation","created":"2025-08-05","cited_by_count":12},{"id":"2601.22347","title":"Pushing the Limits of Block Rotations in Post-Training Quantization","created":"2026-01-29","cited_by_count":11},{"id":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","cited_by_count":11},{"id":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10},{"id":"2510.05373","title":"KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction","created":"2025-10-06","cited_by_count":10},{"id":"2601.09555","title":"Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats","created":"2026-01-14","cited_by_count":10},{"id":"2310.10944","title":"TEQ: Trainable Equivalent Transformation for Quantization of LLMs","created":"2023-10-17","cited_by_count":9},{"id":"2502.00922","title":"Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference","created":"2025-02-02","cited_by_count":9},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9},{"id":"2605.13810","title":"Provable Quantization with Randomized Hadamard Transform","created":"2026-05-13","cited_by_count":8},{"id":"2506.05432","title":"PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling","created":"2025-06-05","cited_by_count":7},{"id":"2506.09932","title":"HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations","created":"2025-06-11","cited_by_count":7},{"id":"2512.03673","title":"ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers","created":"2025-12-03","cited_by_count":7},{"id":"2601.17187","title":"High-Rate Quantized Matrix Multiplication I","created":"2026-01-23","cited_by_count":7},{"id":"2605.06014","title":"Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven","created":"2026-05-07","cited_by_count":6},{"id":"2312.03788","title":"SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM","created":"2023-12-06","cited_by_count":5},{"id":"2409.20361","title":"Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference","created":"2024-09-30","cited_by_count":5},{"id":"2506.15689","title":"BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models","created":"2025-05-26","cited_by_count":5},{"id":"2603.04359","title":"Dissecting Quantization Error: A Concentration-Alignment Perspective","created":"2026-03-04","cited_by_count":5},{"id":"2604.08826","title":"HiFloat4 Format for Language Model Pre-training on Ascend NPUs","created":"2026-04-09","cited_by_count":5},{"id":"2605.16732","title":"DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers","created":"2026-05-16","cited_by_count":5},{"id":"2605.29843","title":"HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization","created":"2026-05-28","cited_by_count":5},{"id":"2503.07654","title":"MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration","created":"2025-03-07","cited_by_count":4},{"id":"2507.07145","title":"CCQ: Convolutional Code for Extreme Low-bit Quantization in LLMs","created":"2025-07-09","cited_by_count":4},{"id":"2603.28765","title":"Adaptive Block-Scaled Data Types","created":"2026-03-30","cited_by_count":4},{"id":"2605.13768","title":"High-Rate Quantized Matrix Multiplication II","created":"2026-05-13","cited_by_count":4},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3},{"id":"2605.19561","title":"TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization","created":"2026-05-19","cited_by_count":3},{"id":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2},{"id":"2605.06067","title":"Normalized Architectures are Natively 4-Bit","created":"2026-05-07","cited_by_count":2},{"id":"2605.10793","title":"ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs","created":"2026-05-11","cited_by_count":2},{"id":"2510.26771","title":"STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization","created":"2025-10-30","cited_by_count":1},{"id":"2512.24124","title":"OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization","created":"2025-12-30","cited_by_count":1},{"id":"2606.08761","title":"APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing","created":"2026-06-07","cited_by_count":1}],"next_cursor":null}