{"total":18,"rows":[{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2601.17187","title":"High-Rate Quantized Matrix Multiplication I","created":"2026-01-23","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":"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":"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":"2607.18745","title":"Contraction-Gauge Preconditioning for Quantized Matrix Multiplication","created":"2026-07-21","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":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.19670","title":"The Asymmetric Harms of LLM Compression","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2608.20873","title":"In-Cell Learning: Language Models That Update Their Own Weights in Sequence Without Changing the File They Ship","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.10010","title":"CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.25188","title":"Transforms for LLM Quantization: The Great Inversion and Format Co-Design","created":"2026-08-25","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":"2610.08231","title":"OSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization","created":"2026-10-06","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":"2610.16020","title":"When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}