{"total":105,"rows":[{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"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":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117,"area":"lr"},{"id":"2306.02272","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","created":"2023-06-04","cited_by_count":114,"area":null},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2305.14152","title":"Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization","created":"2023-05-23","cited_by_count":100,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"area":null},{"id":"2402.10517","title":"Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs","created":"2024-02-16","cited_by_count":54,"area":null},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2308.12261","title":"Prompt2Model: Generating Deployable Models from Natural Language Instructions","created":"2023-08-23","cited_by_count":41,"area":null},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"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":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"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":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"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":"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":"2501.14794","title":"Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference","created":"2025-01-11","cited_by_count":22,"area":null},{"id":"2502.11880","title":"Bitnet.cpp: Efficient Edge Inference for Ternary LLMs","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2306.08162","title":"INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation","created":"2023-06-13","cited_by_count":20,"area":null},{"id":"2311.05161","title":"Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization","created":"2023-11-09","cited_by_count":20,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2406.00025","title":"SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","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":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2410.16144","title":"1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs","created":"2024-10-21","cited_by_count":12,"area":null},{"id":"2407.11534","title":"LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices","created":"2024-07-16","cited_by_count":11,"area":null},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","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":"2505.16162","title":"KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization","created":"2025-05-22","cited_by_count":11,"area":"inference"},{"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":"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":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","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":"2510.10467","title":"AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2504.02658","title":"MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators","created":"2025-04-03","cited_by_count":8,"area":"moe"},{"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":"2411.07942","title":"Towards Low-bit Communication for Tensor Parallel LLM Inference","created":"2024-11-12","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":"2309.16119","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","created":"2023-09-28","cited_by_count":6,"area":null},{"id":"2503.15465","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","created":"2025-03-19","cited_by_count":6,"area":"diffusion"},{"id":"2509.13765","title":"TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2411.16158","title":"MixPE: Quantization and Hardware Co-design for Efficient LLM Inference","created":"2024-11-25","cited_by_count":5,"area":"inference"},{"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":"2508.16785","title":"Interpreting the Effects of Quantization on LLMs","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2603.25284","title":"SliderQuant: Accurate Post-Training Quantization for LLMs","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2407.02891","title":"GPTQT: Quantize Large Language Models Twice to Push the Efficiency","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2410.12119","title":"Scaling Laws for Post Training Quantized Large Language Models","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2412.03599","title":"CPTQuant - A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","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":"2410.14570","title":"Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2412.15750","title":"Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference","created":"2024-12-20","cited_by_count":3,"area":"mechinterp"},{"id":"2511.00812","title":"LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2511.06838","title":"P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats","created":"2025-11-10","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":"2401.05391","title":"Efficient LLM inference solution on Intel GPU","created":"2023-12-19","cited_by_count":2,"area":"inference"},{"id":"2403.06497","title":"QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2507.23035","title":"OASIS: Outlier-Aware LUT-Based GEMM with Dual-Side Quantization for LLM Inference Acceleration","created":"2025-07-30","cited_by_count":2,"area":"inference"},{"id":"2511.21910","title":"Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication","created":"2025-11-26","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":"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":"2405.17233","title":"CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2505.05619","title":"LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities","created":"2025-05-08","cited_by_count":1,"area":"safety"},{"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":"2507.01900","title":"High-Layer Attention Pruning with Rescaling","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2508.17069","title":"Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2601.03484","title":"From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs","created":"2026-01-07","cited_by_count":1,"area":"agents"},{"id":"2602.01027","title":"SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.02707","title":"Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.25183","title":"Hardware Generation and Exploration of Lookup Table-Based Accelerators for 1.58-bit LLM Inference","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2309.15531","title":"Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models","created":"2023-09-27","cited_by_count":0,"area":"lr"},{"id":"2405.14597","title":"Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2409.18772","title":"A method of using RSVD in residual calculation of LowBit GEMM","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2412.19002","title":"Tempus Core: Area-Power Efficient Temporal-Unary Convolution Core for Low-Precision Edge DLAs","created":"2024-12-25","cited_by_count":0,"area":null},{"id":"2502.18627","title":"PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.23817","title":"MVDRAM: Enabling GeMV Execution in Unmodified DRAM for Low-Bit LLM Acceleration","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2510.19482","title":"ELUTQ: Optimizing Quantization Accuracy under LUT-Based Computation for Edge LLMs","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2602.15720","title":"ToaSt: Token Channel Selection and Structured Pruning for Efficient ViT","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.22592","title":"pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.02556","title":"Fast NF4 Dequantization Kernels for Large Language Model Inference","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.10496","title":"CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts","created":"2026-04-12","cited_by_count":0,"area":"moe"},{"id":"2605.01935","title":"ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGA","created":"2026-05-03","cited_by_count":0,"area":"ssm"}],"next_cursor":"100"}