{"total":61,"rows":[{"id":"2406.11235","title":"QTIP: Quantization with Trellises and Incoherence Processing","created":"2024-06-17","cited_by_count":91,"area":null},{"id":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"area":null},{"id":"2506.17419","title":"UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making","created":"2025-06-20","cited_by_count":42,"area":"agents"},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"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":"2501.19392","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","created":"2025-01-31","cited_by_count":24,"area":"inference"},{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"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":"2502.12346","title":"QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models","created":"2025-02-17","cited_by_count":11,"area":null},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"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":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2504.05346","title":"Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2504.07389","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","created":"2025-04-10","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":"2409.18850","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2512.01546","title":"LPCD: Unified Framework from Layer-Wise to Submodule Quantization","created":"2025-12-01","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":"2510.23926","title":"Improving the Straight-Through Estimator with Zeroth-Order Information","created":"2025-10-27","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":"2501.18980","title":"Symmetric Pruning of Large Language Models","created":"2025-01-31","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":"2509.23729","title":"LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models","created":"2025-09-28","cited_by_count":3,"area":"mllm"},{"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":"2603.28845","title":"OneComp: One-Line Revolution for Generative AI Model Compression","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2604.07888","title":"Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2602.01410","title":"SNIP: An Adaptive Mixed Precision Framework for Subbyte Large Language Model Training","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2605.24144","title":"EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2605.25469","title":"JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates","created":"2026-05-25","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":"2503.13089","title":"ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning","created":"2025-03-17","cited_by_count":1,"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":"2505.17595","title":"NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs","created":"2025-05-23","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":"2601.01296","title":"Aggressive Compression Enables LLM Weight Theft","created":"2026-01-03","cited_by_count":1,"area":"safety"},{"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":"2603.01599","title":"Boosting Entropy with Bell Box Quantization","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2608.07019","title":"ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.30908","title":"Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2506.05960","title":"AQUATIC-Diff: Additive Quantization for Truly Tiny Compressed Diffusion Models","created":"2025-06-06","cited_by_count":0,"area":"diffusion"},{"id":"2601.20745","title":"HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.24595","title":"M2K: Making the Model-Kernel Interface Explicit for Reliable CUDA Kernel Verification","created":"2026-03-06","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":"2605.09425","title":"AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation","created":"2026-05-10","cited_by_count":0,"area":"diffusion"},{"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":"2607.10855","title":"Reliability Scaling Laws for Quantized Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.25977","title":"When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.00049","title":"REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.12208","title":"Vortex: Bridging Extreme Compression and Efficient LLM Inference","created":"2026-09-10","cited_by_count":0,"area":"inference"},{"id":"2609.32659","title":"Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution","created":"2026-09-26","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":"2610.00738","title":"Q-MINO: A Minimal-Norm Method for Quantization-Aware Training","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04490","title":"BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.09202","title":"Few Bits, One Law: Toward W2A4KV2","created":"2026-10-06","cited_by_count":0,"area":"inference"},{"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}],"next_cursor":null}