{"total":47,"rows":[{"id":"2604.18555","title":"A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2601.17187","title":"High-Rate Quantized Matrix Multiplication I","created":"2026-01-23","cited_by_count":7,"area":null},{"id":"2604.14442","title":"Hierarchical vs. Flat Iteration in Shared-Weight Transformers","created":"2026-04-15","cited_by_count":4,"area":null},{"id":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2605.25880","title":"The Quantization Benefits of Residual-Free Transformers","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2604.19528","title":"Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments","created":"2026-04-21","cited_by_count":3,"area":null},{"id":"2603.29078","title":"PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.23418","title":"Approximating Uniform Random Rotations by Two-Stage Structured Hadamard Rotations in High Dimensions","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2608.08253","title":"SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents","created":"2026-08-08","cited_by_count":2,"area":null},{"id":"2605.15507","title":"PrismQuant: Rate-Distortion-Optimal Vector Quantization for Gaussian-Mixture Sources","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.01074","title":"When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression","created":"2026-05-31","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":"2606.08761","title":"APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2607.27546","title":"Memory Efficient Tabular Foundation Models","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2602.00079","title":"Embedding Compression via Spherical Coordinates","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.00165","title":"Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.05366","title":"3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.21026","title":"MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.22786","title":"AutoCompress: Critical Layer Isolation for Efficient Transformer Compression","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.24008","title":"Coverage-Based Calibration for Post-Training Quantization via Weighted Set Cover over Outlier Channels","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.07662","title":"Direction-Preserving Number Representations","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.17415","title":"IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.19972","title":"Block-Sphere Vector Quantization","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.00289","title":"Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.08565","title":"EinSort: Sorting is All We Need for Tensorizing LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.19562","title":"Advances in Scientific Machine Learning for Coupled Fluid Flow and Transport","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20474","title":"UltraQuant: 4-bit KV Caching for Context-Heavy Agents","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.05127","title":"SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.11240","title":"VQ-bench: A Composable Vector Quantization Framework","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.13365","title":"When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.14648","title":"Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.15369","title":"AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.24971","title":"HCC+: Hyperbolic Guarding for Certified Attention Retrieval","created":"2026-08-25","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":"2608.30384","title":"RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.08759","title":"A Note on Scaling in Randomly Rotated Quantization and Its Connection to the CDEF +1 Pythagorean Relation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.30950","title":"Low-Bit Recurrent States in Hybrid Language Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33965","title":"Greenpixie's AI Token Methodology: Assessing the Energy, Water and CO2-eq Impact of AI Tokens for Open and Closed Weight Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36032","title":"TORQUE: Optimizing What (not) to Quantize Before and After Rotation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36760","title":"QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38166","title":"LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.07904","title":"ApexQuant: Data-Free Elastic Quantization by Residual Re-Isotropization","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13767","title":"DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14703","title":"Linear-Time Non-Local Codec Placement for Machine Learning Model Compression","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}