{"total":159,"rows":[{"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":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"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":"2402.11295","title":"OneBit: Towards Extremely Low-bit Large Language Models","created":"2024-02-17","cited_by_count":79,"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":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2407.00088","title":"T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge","created":"2024-06-25","cited_by_count":55,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49,"area":null},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"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":"2407.09424","title":"TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2505.19115","title":"FP4 All the Way: Fully Quantized Training of LLMs","created":"2025-05-25","cited_by_count":40,"area":null},{"id":"2505.14669","title":"Quartet: Native FP4 Training Can Be Optimal for Large Language Models","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2406.03287","title":"SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"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":"2412.18653","title":"1.58-bit FLUX","created":"2024-12-24","cited_by_count":31,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2406.02528","title":"Scalable MatMul-free Language Modeling","created":"2024-06-04","cited_by_count":25,"area":null},{"id":"2407.10969","title":"Q-Sparse: All Large Language Models can be Fully Sparsely-Activated","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2408.04585","title":"Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness","created":"2024-08-08","cited_by_count":22,"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":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"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":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"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":"2411.04965","title":"BitNet a4.8: 4-bit Activations for 1-bit LLMs","created":"2024-11-07","cited_by_count":16,"area":null},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2407.07093","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","created":"2024-07-09","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":"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":"2502.16440","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","created":"2025-02-23","cited_by_count":11,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2504.16266","title":"TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs","created":"2025-04-22","cited_by_count":10,"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":"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":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2509.23809","title":"Tequila: Trapping-free Ternary Quantization for Large Language Models","created":"2025-09-28","cited_by_count":9,"area":null},{"id":"2407.09527","title":"BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks","created":"2024-06-24","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":"2410.15116","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2505.17101","title":"A quantitative analysis of semantic information in deep representations of text and images","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2406.16893","title":"A Survey of Transformer-based Language Models with Focus on Efficiency","created":"2024-05-15","cited_by_count":6,"area":null},{"id":"2502.16473","title":"TerEffic: Highly Efficient Ternary LLM Inference on FPGA","created":"2025-02-23","cited_by_count":6,"area":null},{"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":"2511.13061","title":"MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity","created":"2025-11-17","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":"2501.19067","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2502.01705","title":"Progressive Binarization with Semi-Structured Pruning for LLMs","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2502.21001","title":"Towards Lossless Implicit Neural Representation via Bit Plane Decomposition","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2507.19608","title":"DeltaLLM: Delta-Key Sparse Attention for Edge LLMs","created":"2025-07-25","cited_by_count":5,"area":null},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2405.02543","title":"Exploring Extreme Quantization in Spiking Language Models","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2406.07247","title":"Dynamical Mean-Field Theory of Self-Attention Neural Networks","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2409.00297","title":"On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic","created":"2024-08-30","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":"2411.01663","title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","created":"2024-11-03","cited_by_count":4,"area":null},{"id":"2503.19353","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2506.12040","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2511.13676","title":"T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2409.09245","title":"Robust Training of Neural Networks at Arbitrary Precision and Sparsity","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2410.05911","title":"Accelerating Error Correction Code Transformers","created":"2024-10-08","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":"2411.06360","title":"An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2501.11847","title":"A Survey on Memory-Efficient Transformer-Based Model Training in AI for Science","created":"2025-01-21","cited_by_count":3,"area":null},{"id":"2504.02118","title":"LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi","created":"2025-04-02","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":"2601.17215","title":"JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers","created":"2026-01-23","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":"2605.17471","title":"WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2411.02126","title":"Unsupervised detection of semantic correlations in big data","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2505.03254","title":"PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.03515","title":"BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.05664","title":"BAQ: Efficient Bit Allocation Quantization for Large Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2506.11044","title":"Boost Post-Training Quantization via Null Space Optimization for Large Language Models","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2509.09424","title":"ENSI: Efficient Non-Interactive Secure Inference for Large Language Models","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2510.13998","title":"BitNet Distillation","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2510.15542","title":"SpikeFit: Towards Optimal Deployment of Spiking Networks on Neuromorphic Hardware","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2511.18474","title":"Adaptive Mesh-Quantization for Neural PDE Solvers","created":"2025-11-23","cited_by_count":2,"area":null},{"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":"2602.02546","title":"D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.18037","title":"Adapting Methods for Domain-Specific Japanese Small LMs: Scale, Architecture, and Quantization","created":"2026-03-12","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":"2402.10474","title":"One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2404.10896","title":"From a Lossless (~1.5:1) Compression Algorithm for Llama2 7B Weights to Variable Precision, Variable Range, Compressed Numeric Data Types for CNNs and LLMs","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2410.01309","title":"Getting Free Bits Back from Rotational Symmetries in LLMs","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2410.09734","title":"Gradient-Free Training of Quantized Neural Networks","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2411.15438","title":"Efficient Ternary Weight Embedding Model: Bridging Scalability and Performance","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2502.01908","title":"Physics-Inspired Binary Neural Networks: Interpretable Compression with Theoretical Guarantees","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2502.19008","title":"Binary Neural Networks for Large Language Model: A Survey","created":"2025-02-26","cited_by_count":1,"area":null}],"next_cursor":"100"}