{"total":173,"rows":[{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"area":null},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378,"area":null},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2406.11235","title":"QTIP: Quantization with Trellises and Incoherence Processing","created":"2024-06-17","cited_by_count":91,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2405.18137","title":"Exploiting LLM Quantization","created":"2024-05-28","cited_by_count":65,"area":null},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59,"area":null},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57,"area":null},{"id":"2408.11743","title":"MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models","created":"2024-08-21","cited_by_count":52,"area":null},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"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":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2407.10960","title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs","created":"2024-07-15","cited_by_count":29,"area":null},{"id":"2404.03605","title":"Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"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":"2410.17770","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","created":"2024-10-23","cited_by_count":21,"area":null},{"id":"2411.17525","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2409.13652","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","created":"2024-09-20","cited_by_count":20,"area":null},{"id":"2410.14649","title":"EvoPress: Accurate Dynamic Model Compression via Evolutionary Search","created":"2024-10-18","cited_by_count":20,"area":null},{"id":"2507.18553","title":"The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm","created":"2025-07-24","cited_by_count":20,"area":null},{"id":"2406.13555","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","created":"2024-06-19","cited_by_count":19,"area":null},{"id":"2411.17691","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","created":"2024-11-26","cited_by_count":18,"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":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2508.04853","title":"Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos","created":"2025-08-06","cited_by_count":16,"area":null},{"id":"2501.02625","title":"HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs","created":"2025-01-05","cited_by_count":15,"area":null},{"id":"2403.09207","title":"TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks","created":"2024-03-14","cited_by_count":14,"area":null},{"id":"2503.05200","title":"ORANSight-2.0: Foundational LLMs for O-RAN","created":"2025-03-07","cited_by_count":13,"area":null},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2406.13474","title":"BoA: Attention-aware Post-training Quantization without Backpropagation","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2503.01483","title":"KurTail : Kurtosis-based LLM Quantization","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10,"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":"2412.01129","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","created":"2024-12-02","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":"2509.16989","title":"PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models","created":"2025-09-21","cited_by_count":9,"area":null},{"id":"2408.15300","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2501.02423","title":"Scaling Laws for Floating Point Quantization Training","created":"2025-01-05","cited_by_count":8,"area":null},{"id":"2405.15025","title":"OAC: Output-adaptive Calibration for Accurate Post-training Quantization","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2412.09282","title":"CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2502.05376","title":"LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference","created":"2025-02-07","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":"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":"2603.04956","title":"WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2505.13430","title":"Fine-tuning Quantized Neural Networks with Zeroth-order Optimization","created":"2025-05-19","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":"2602.05902","title":"CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization","created":"2026-02-05","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":"2412.17560","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","created":"2024-12-23","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2505.03031","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2506.03781","title":"Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2506.12024","title":"FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2507.04610","title":"any4: Learned 4-bit Numeric Representation for LLMs","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2508.03332","title":"Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models","created":"2025-08-05","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":"2406.17542","title":"CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2410.10714","title":"SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2410.19103","title":"TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction","created":"2024-10-24","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":"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":"2405.13155","title":"ReALLM: A general framework for LLM compression and fine-tuning","created":"2024-05-21","cited_by_count":3,"area":null},{"id":"2501.06417","title":"DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory","created":"2025-01-11","cited_by_count":3,"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":"2510.12721","title":"CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2511.17637","title":"PocketLLM: Ultimate Compression of Large Language Models via Meta Networks","created":"2025-11-19","cited_by_count":3,"area":null},{"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":"2601.19675","title":"LoPRo: Enhancing Low-Rank Quantization via Permuted Block-Wise Rotation","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2602.17698","title":"ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs","created":"2026-02-06","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":"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":"2405.01943","title":"Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2406.00061","title":"STAT: Shrinking Transformers After Training","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2409.02026","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2410.06722","title":"Scaling Laws For Mixed Quantization","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2412.07902","title":"Low-Rank Correction for Quantized LLMs","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","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":"2510.19105","title":"MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2512.02901","title":"Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\\{\\pm 1, \\pm i\\}$","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2601.22787","title":"Float8@2bits: Entropy Coding Enables Data-Free Model Compression","created":"2026-01-30","cited_by_count":2,"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":"2605.04062","title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","created":"2026-04-10","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}],"next_cursor":"100"}