{"total":378,"rows":[{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634,"area":"inference"},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471,"area":"inference"},{"id":"2402.17764","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","created":"2024-02-27","cited_by_count":308,"area":null},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"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":"2501.13987","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","created":"2025-01-23","cited_by_count":97,"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":"2402.11295","title":"OneBit: Towards Extremely Low-bit Large Language Models","created":"2024-02-17","cited_by_count":79,"area":null},{"id":"2509.25149","title":"Pretraining Large Language Models with NVFP4","created":"2025-09-29","cited_by_count":76,"area":null},{"id":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"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":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"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":"2408.14690","title":"Training-Free Activation Sparsity in Large Language Models","created":"2024-08-26","cited_by_count":55,"area":"inference"},{"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":"2410.06270","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More","created":"2024-10-08","cited_by_count":41,"area":"moe"},{"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":"2501.13484","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","created":"2025-01-23","cited_by_count":29,"area":"ssm"},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2410.13229","title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","created":"2024-10-17","cited_by_count":28,"area":"ssm"},{"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":"2407.18158","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","created":"2024-07-25","cited_by_count":25,"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":"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":"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":"2408.08554","title":"ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models","created":"2024-08-16","cited_by_count":22,"area":"inference"},{"id":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","cited_by_count":22,"area":null},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"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":"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":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20,"area":null},{"id":"2509.21302","title":"Quantized Visual Geometry Grounded Transformer","created":"2025-09-25","cited_by_count":17,"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":"2511.10645","title":"ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference","created":"2025-11-13","cited_by_count":17,"area":"lr"},{"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":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","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":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2501.02625","title":"HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs","created":"2025-01-05","cited_by_count":15,"area":null},{"id":"2505.18663","title":"DVD-Quant: Data-free Video Diffusion Transformers Quantization","created":"2025-05-24","cited_by_count":15,"area":"diffusion"},{"id":"2509.09090","title":"SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models","created":"2025-09-11","cited_by_count":15,"area":"vla"},{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","cited_by_count":15,"area":null},{"id":"2512.00956","title":"WUSH: Near-Optimal Adaptive Transforms for LLM Quantization","created":"2025-11-30","cited_by_count":15,"area":null},{"id":"2601.07475","title":"ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs","created":"2026-01-12","cited_by_count":15,"area":null},{"id":"2403.02694","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","created":"2024-03-05","cited_by_count":14,"area":null},{"id":"2410.13780","title":"Optimal Quantization for Matrix Multiplication","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2503.16257","title":"Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models","created":"2025-03-20","cited_by_count":13,"area":"inference"},{"id":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","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":"2405.20835","title":"Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs","created":"2024-05-31","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":"2411.11843","title":"Bi-Mamba: Towards Accurate 1-Bit State Space Models","created":"2024-11-18","cited_by_count":12,"area":"ssm"},{"id":"2412.08832","title":"HadaCore: Tensor Core Accelerated Hadamard Transform Kernel","created":"2024-12-12","cited_by_count":12,"area":null},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","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":"2508.03485","title":"LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation","created":"2025-08-05","cited_by_count":12,"area":"diffusion"},{"id":"2410.08391","title":"KV Prediction for Improved Time to First Token","created":"2024-10-10","cited_by_count":11,"area":"inference"},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2501.01144","title":"BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference","created":"2025-01-02","cited_by_count":11,"area":"inference"},{"id":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","cited_by_count":11,"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":"2509.23106","title":"Effective Quantization of Muon Optimizer States","created":"2025-09-27","cited_by_count":11,"area":null},{"id":"2606.08382","title":"STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control","created":"2026-06-07","cited_by_count":11,"area":"inference"},{"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":"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":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2411.15982","title":"Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"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":"2501.10658","title":"LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator","created":"2025-01-18","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":"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":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"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":"2601.14277","title":"Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instruct","created":"2026-01-11","cited_by_count":8,"area":null},{"id":"2601.19213","title":"M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2602.11184","title":"KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models","created":"2026-01-30","cited_by_count":8,"area":"moe"},{"id":"2604.17789","title":"DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization","created":"2026-04-20","cited_by_count":8,"area":"inference"},{"id":"2605.13810","title":"Provable Quantization with Randomized Hadamard Transform","created":"2026-05-13","cited_by_count":8,"area":"inference"},{"id":"2405.15025","title":"OAC: Output-adaptive Calibration for Accurate Post-training Quantization","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2410.21271","title":"EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation","created":"2024-10-28","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}],"next_cursor":"100"}