{"total":70,"rows":[{"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":"2508.14896","title":"Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs","created":"2025-08-20","cited_by_count":23,"area":null},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2511.04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2603.21389","title":"Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models","created":"2026-03-22","cited_by_count":15,"area":null},{"id":"2503.01483","title":"KurTail : Kurtosis-based LLM Quantization","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2601.22347","title":"Pushing the Limits of Block Rotations in Post-Training Quantization","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2511.11663","title":"SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization","created":"2025-11-11","cited_by_count":10,"area":null},{"id":"2511.15580","title":"CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking","created":"2025-11-19","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":"2602.24133","title":"FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking","created":"2026-02-27","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":"2509.11177","title":"Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs","created":"2025-09-14","cited_by_count":6,"area":null},{"id":"2605.16343","title":"LoopQ: Quantization for Looped Language Models","created":"2026-05-08","cited_by_count":6,"area":null},{"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,"area":null},{"id":"2511.06863","title":"VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling","created":"2025-11-10","cited_by_count":5,"area":null},{"id":"2603.04359","title":"Dissecting Quantization Error: A Concentration-Alignment Perspective","created":"2026-03-04","cited_by_count":5,"area":null},{"id":"2605.00422","title":"BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2503.19353","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2505.03803","title":"RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization","created":"2025-05-02","cited_by_count":4,"area":null},{"id":"2506.01352","title":"TAH-QUANT: Effective Activation Quantization in Pipeline Parallelism over Slow Network","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2506.12040","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2509.11453","title":"Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking","created":"2025-09-14","cited_by_count":4,"area":null},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2505.03810","title":"Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2602.04929","title":"TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2605.19561","title":"TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization","created":"2026-05-19","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":"2607.07964","title":"KronQ: LLM Quantization via Kronecker-Factored Hessian","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2502.15488","title":"FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection","created":"2025-02-21","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":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2604.11080","title":"ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2606.07618","title":"ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2607.18745","title":"Contraction-Gauge Preconditioning for Quantized Matrix Multiplication","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.01847","title":"FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2505.17595","title":"NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2511.17809","title":"Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2511.22316","title":"Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.24124","title":"OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2601.21626","title":"HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.02988","title":"NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.08185","title":"SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization","created":"2026-03-09","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":"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":"2609.31291","title":"Softmax Reparameterization for Output-Head Quantization","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2511.09347","title":"FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2604.26378","title":"CoQuant: Joint Weight-Activation Subspace Projection for Mixed-Precision LLMs","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.18800","title":"Theory-optimal Quantization Based on Flatness","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.26175","title":"InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.26587","title":"SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.08643","title":"BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.20434","title":"Break Through the Compression Bottleneck: From Theory to Practice","created":"2026-05-11","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":"2608.24173","title":"SandwichQuant: Which Parameters Matter Before and After Quantization?","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29111","title":"Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.24799","title":"When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.31009","title":"G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32429","title":"PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36120","title":"ThinQuant: Scalable Rotation Learning for Weight and Activation Quantization of LLMs","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":"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":"2610.20303","title":"SpectrumQuant: Spectrum Alignment for LLM Quantization","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}