{"total":19,"rows":[{"id":"2512.00956","title":"WUSH: Near-Optimal Adaptive Transforms for LLM Quantization","created":"2025-11-30","cited_by_count":15,"area":null},{"id":"2508.01077","title":"The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's Algorithm","created":"2025-08-01","cited_by_count":9,"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":"2602.05902","title":"CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2605.13768","title":"High-Rate Quantized Matrix Multiplication II","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2602.04163","title":"BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2607.27042","title":"GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding","created":"2026-07-29","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":"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":"2602.08376","title":"OJBKQ: Objective-Joint Babai-Klein Quantization","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.26092","title":"GoQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2608.06291","title":"FastKron: Efficient Quantization with Kronecker-Factored Hessians","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2608.15567","title":"SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization","created":"2026-08-16","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":"2609.31560","title":"Generalization behavior of OPTQ and the role of regularization","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31641","title":"Product-Aware Deterministic Rounding for Quantized Matrix Multiplication","created":"2026-09-11","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":"2609.38599","title":"JARQ: Joint Alternating Refinement for Quantization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.18139","title":"Revisiting Error Feedback for Model Quantization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}