{"total":71,"rows":[{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2505.11695","title":"Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization","created":"2025-05-16","cited_by_count":28,"area":null},{"id":"2502.09720","title":"NestQuant: Nested Lattice Quantization for Matrix Products and LLMs","created":"2025-02-13","cited_by_count":23,"area":null},{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2507.18553","title":"The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm","created":"2025-07-24","cited_by_count":20,"area":null},{"id":"2412.14590","title":"MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design","created":"2024-12-19","cited_by_count":16,"area":null},{"id":"2512.00956","title":"WUSH: Near-Optimal Adaptive Transforms for LLM Quantization","created":"2025-11-30","cited_by_count":15,"area":null},{"id":"2410.13780","title":"Optimal Quantization for Matrix Multiplication","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2505.00850","title":"ICQuant: Index Coding enables Low-bit LLM Quantization","created":"2025-05-01","cited_by_count":9,"area":null},{"id":"2509.16989","title":"PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models","created":"2025-09-21","cited_by_count":9,"area":null},{"id":"2509.20214","title":"Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment","created":"2025-09-24","cited_by_count":8,"area":null},{"id":"2506.05432","title":"PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling","created":"2025-06-05","cited_by_count":7,"area":null},{"id":"2603.04956","title":"WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2603.11021","title":"Leech Lattice Vector Quantization for Efficient LLM Compression","created":"2026-03-11","cited_by_count":7,"area":null},{"id":"2505.23049","title":"DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2511.13061","title":"MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity","created":"2025-11-17","cited_by_count":6,"area":null},{"id":"2604.18556","title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","created":"2026-04-20","cited_by_count":6,"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":"2508.03332","title":"Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2605.29843","title":"HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2507.07145","title":"CCQ: Convolutional Code for Extreme Low-bit Quantization in LLMs","created":"2025-07-09","cited_by_count":4,"area":null},{"id":"2510.20984","title":"Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2605.13768","title":"High-Rate Quantized Matrix Multiplication II","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2501.06417","title":"DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2503.01820","title":"RSQ: Learning from Important Tokens Leads to Better Quantized LLMs","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2505.11076","title":"Addition is almost all you need: Compressing large language models with double binary factorization","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2509.23410","title":"PATCH: Learnable Tile-level Hybrid Sparsity for LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2511.17637","title":"PocketLLM: Ultimate Compression of Large Language Models via Meta Networks","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2512.17970","title":"CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2512.24545","title":"More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2602.17698","title":"ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2606.10531","title":"LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization","created":"2026-06-09","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":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.01240","title":"RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2602.02546","title":"D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2605.04062","title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2605.10793","title":"ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.12327","title":"Grid Games: The Power of Multiple Grids for Quantizing Large Language Models","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.04050","title":"LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2608.12026","title":"SoftWater: Class-Aware Rate Allocation for Softmax Quantization","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2504.14569","title":"NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2505.12988","title":"Optimal Formats for Weight Quantisation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2510.11234","title":"Neural Weight Compression for Language Models","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2511.19705","title":"CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.05790","title":"Price of metric universality in vector quantization is at most 0.11 bit","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2602.06694","title":"NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.20191","title":"MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.04162","title":"Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2605.18475","title":"GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.20402","title":"Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.26339","title":"QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.13966","title":"QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2509.18172","title":"SBVR: Summation of BitVector Representation for Efficient LLM Quantization","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2602.05367","title":"RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.08118","title":"Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.10655","title":"BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27808","title":"TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2609.11687","title":"Structured Transforms for Low-Overhead Quantization of Language Models","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.14706","title":"WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.28270","title":"Predicting Quantization Price for Selecting PTQ Configurations Before Deployment","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.34185","title":"EntroPack: Fast and Accurate Entropy-Coded Weight Compression at Arbitrary Bitrates","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35465","title":"Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00432","title":"XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02598","title":"Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.14745","title":"SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16289","title":"Fast Quantized Johnson$-$Lindenstrauss Transforms","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}