{"total":471,"rows":[{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170,"area":"diffusion"},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2406.02540","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","created":"2024-06-04","cited_by_count":115,"area":"diffusion"},{"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":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"id":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2411.07191","title":"The Super Weight in Large Language Models","created":"2024-11-11","cited_by_count":52,"area":null},{"id":"2501.16383","title":"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations","created":"2025-01-25","cited_by_count":46,"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":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45,"area":"mllm"},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2411.10666","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","created":"2024-11-16","cited_by_count":39,"area":"inference"},{"id":"2406.04333","title":"BitsFusion: 1.99 bits Weight Quantization of Diffusion Model","created":"2024-06-06","cited_by_count":37,"area":"diffusion"},{"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":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35,"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":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"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":"2602.03782","title":"QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization","created":"2026-02-03","cited_by_count":28,"area":"vla"},{"id":"2507.16099","title":"TorchAO: PyTorch-Native Training-to-Serving Model Optimization","created":"2025-07-21","cited_by_count":26,"area":null},{"id":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23,"area":null},{"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":"2511.14582","title":"OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models","created":"2025-11-18","cited_by_count":22,"area":"inference"},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"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":"2412.11549","title":"MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models","created":"2024-12-16","cited_by_count":21,"area":"diffusion"},{"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":"2505.02214","title":"An Empirical Study of Qwen3 Quantization","created":"2025-05-04","cited_by_count":21,"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":"2411.09909","title":"AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference","created":"2024-11-15","cited_by_count":19,"area":null},{"id":"2504.18415","title":"BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs","created":"2025-04-25","cited_by_count":18,"area":null},{"id":"2510.25602","title":"INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats","created":"2025-10-29","cited_by_count":18,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","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":"2411.04965","title":"BitNet a4.8: 4-bit Activations for 1-bit LLMs","created":"2024-11-07","cited_by_count":16,"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":"2503.22879","title":"Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models","created":"2025-03-28","cited_by_count":16,"area":"ssm"},{"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":"2509.00190","title":"Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics","created":"2025-08-29","cited_by_count":16,"area":"lr"},{"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":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"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":"2512.00956","title":"WUSH: Near-Optimal Adaptive Transforms for LLM Quantization","created":"2025-11-30","cited_by_count":15,"area":null},{"id":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2503.18599","title":"Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization","created":"2025-03-24","cited_by_count":14,"area":"inference"},{"id":"2504.20437","title":"GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection","created":"2025-04-29","cited_by_count":14,"area":null},{"id":"2510.27527","title":"TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control","created":"2025-10-31","cited_by_count":14,"area":null},{"id":"2407.08044","title":"RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2506.07851","title":"Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning","created":"2025-06-09","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":"2406.13474","title":"BoA: Attention-aware Post-training Quantization without Backpropagation","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2410.05265","title":"PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization","created":"2024-10-07","cited_by_count":12,"area":null},{"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":"2506.13045","title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","created":"2025-06-16","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":"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":"2502.15260","title":"LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design","created":"2025-02-21","cited_by_count":11,"area":"ssm"},{"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":"2508.02343","title":"MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models","created":"2025-08-04","cited_by_count":11,"area":null},{"id":"2509.23324","title":"Scaling LLM Test-Time Compute with Mobile NPU on Smartphones","created":"2025-09-27","cited_by_count":11,"area":"lr"},{"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":"2506.13329","title":"EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization","created":"2025-06-16","cited_by_count":10,"area":"moe"},{"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":"2510.05373","title":"KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction","created":"2025-10-06","cited_by_count":10,"area":"inference"},{"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":"2601.09555","title":"Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats","created":"2026-01-14","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":"2501.15021","title":"AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models","created":"2025-01-25","cited_by_count":9,"area":"mllm"},{"id":"2504.14152","title":"FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference","created":"2025-04-19","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":"2506.12044","title":"Why Do Some Inputs Break Low-Bit LLM Quantization?","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","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":"2411.07762","title":"ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2507.11017","title":"First-Order Error Matters: Accurate Compensation for Quantized Large Language Models","created":"2025-07-15","cited_by_count":8,"area":null},{"id":"2508.03351","title":"SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models","created":"2025-08-05","cited_by_count":8,"area":"mllm"},{"id":"2509.01229","title":"LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving","created":"2025-09-01","cited_by_count":8,"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":"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":"2603.17435","title":"ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression","created":"2026-03-18","cited_by_count":8,"area":"inference"},{"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":"2505.14742","title":"Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2505.18231","title":"NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache","created":"2025-05-23","cited_by_count":7,"area":"inference"},{"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":"2506.09932","title":"HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations","created":"2025-06-11","cited_by_count":7,"area":"diffusion"},{"id":"2512.03673","title":"ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers","created":"2025-12-03","cited_by_count":7,"area":"diffusion"}],"next_cursor":"100"}