{"total":32,"rows":[{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853,"area":null},{"id":"2310.08659","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","created":"2023-10-12","cited_by_count":196,"area":null},{"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":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95,"area":null},{"id":"2303.14341","title":"Towards Accurate Post-Training Quantization for Vision Transformer","created":"2023-03-25","cited_by_count":71,"area":null},{"id":"2306.00317","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","created":"2023-06-01","cited_by_count":48,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2401.11033","title":"FAIR Enough: How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training?","created":"2024-01-19","cited_by_count":9,"area":null},{"id":"2208.12866","title":"Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","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":"2405.02543","title":"Exploring Extreme Quantization in Spiking Language Models","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2511.13254","title":"Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2512.13733","title":"Low-Rank Compression of Language Models via Differentiable Rank Selection","created":"2025-12-14","cited_by_count":4,"area":null},{"id":"2306.04879","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2411.03697","title":"TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2310.13315","title":"Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2310.19624","title":"Exploring Post-Training Quantization of Protein Language Models","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2310.19902","title":"Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2405.20973","title":"LCQ: Low-Rank Codebook based Quantization for Large Language Models","created":"2024-05-31","cited_by_count":1,"area":null},{"id":"2406.02599","title":"Privacy-Aware Randomized Quantization via Linear Programming","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2407.10115","title":"A Bag of Tricks for Scaling CPU-based Deep FFMs to more than 300m Predictions per Second","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2601.22716","title":"Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2304.02481","title":"Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2401.12295","title":"Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2404.04759","title":"What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2408.02685","title":"Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2608.14149","title":"QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}