AI Research

AI & ML Research Papers

A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.

Quantization

42 papers

JournalIEEE Internet of Things Journal2024

EdgeShard: Efficient LLM Inference via Collaborative Edge Computing

Mingjin Zhang, Xiaoming Shen, Jiannong Cao, et al.

EdgeShard partitions LLMs into shards across collaborative edge devices and cloud, using dynamic programming to optimize latency and throughput without accuracy loss.

226Dec 31, 2024Large Language ModelsQuantization

ConferenceTransactions of the Association for Computational Linguistics2024

A Survey on Model Compression for Large Language Models

Xunyu Zhu, Jian Li, Yong Liu, et al.

This survey reviews model compression techniques for large language models, covering quantization, pruning, and knowledge distillation, along with benchmarking and evaluation metrics.

539Jan 1, 2024Large Language ModelsBenchmarks

arXiv

JournalProceedings of the IEEE1975

Linear prediction: A tutorial review

J. Makhoul

A tutorial review of linear prediction for discrete signals, covering all-pole and pole-zero models, least squares estimation, spectral matching, and applications to data compression.

4.0kJan 1, 1975Attention MechanismsQuantization

JournalIEEE Transactions on Big Data2019

Billion-Scale Similarity Search with GPUs

Jeff Johnson, Matthijs Douze, Hervé Jeǵou

Proposes a novel GPU k-selection design that accelerates brute-force, approximate, and product-quantization-based similarity search, achieving up to 8.5x speedup over prior GPU state of the art.

4.1kJun 7, 2019Quantization

Preprint2025

Q-dit: Accurate post-training quantization for diffusion transformers

Unknown

Q-dit introduces a post-training quantization method for diffusion transformers that reduces memory and latency while maintaining generation quality.

0Jan 1, 2025TransformersDiffusion Models

Preprint2025

A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference: S …

Unknown

A privacy-preserving FCNN framework using TFHE-based inference for secure medical image analysis on MedMNIST.

0Jan 1, 2025QuantizationNeural Networks

JournalACM Transactions on Internet of Things2025

Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency

Erik Johannes Husom, Arda Göknil, Merve Astekin, et al.

This paper evaluates 28 quantized LLMs on a Raspberry Pi 4, measuring energy efficiency, accuracy, and latency to identify optimal configurations for sustainable edge AI deployment.

67Sep 17, 2025Large Language ModelsBenchmarks

arXiv

Preprint2026

ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization

He-Yen Hsieh, H. T. Kung

ReRound is a post-training quantization method that uses a conditional diffusion model to resolve midpoint ambiguity in round-to-nearest, improving low-bit LLM quantization without calibration data.

0Aug 11, 2026Diffusion ModelsQuantization

arXiv

Preprint2024

Cachegen: Kv cache compression and streaming for fast large language model serving

Unknown

CacheGen reduces KV cache loading delay by 1.67-1.81x versus 8-bit quantization while achieving nearly lossless compression for fast LLM serving.

0Jan 1, 2024Large Language ModelsQuantization

Preprint2024

UAV-deployed deep learning network for real-time multi-class damage detection using model quantization techniques

Unknown

This paper proposes a UAV-deployed deep learning network for real-time multi-class damage detection, enhanced by model quantization techniques.

0Jan 1, 2024Quantization

Preprint2025

Aggregating empirical evidence from data strategy studies: a case on model quantization

Unknown

This study aggregates empirical evidence from data strategy studies to assess the effects of model quantization, finding a weak negative impact.

0May 1, 2025Quantization

arXiv

Preprint2021

Locality-based encoder and model quantization for efficient hyper-dimensional computing

Unknown

This paper proposes locality-based encoding and model quantization to improve efficiency of hyper-dimensional computing for machine learning tasks.

0Jan 1, 2021Quantization