A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
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.
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.
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.
Unknown
This paper proposes a UAV-deployed deep learning network for real-time multi-class damage detection, enhanced by model quantization techniques.
Unknown
This study aggregates empirical evidence from data strategy studies to assess the effects of model quantization, finding a weak negative impact.
Unknown
This paper proposes locality-based encoding and model quantization to improve efficiency of hyper-dimensional computing for machine learning tasks.
Unknown
Quantsparse is a unified framework that integrates model quantization with attention sparsification to comprehensively compress video diffusion transformers.
Unknown
This paper proposes a generative data-free quantization method that uses knowledge matching to synthesize informative training data, improving quantized model performance.
Unknown
This paper quantitatively analyzes the performance drop in DeepSeek model quantization, aiming to answer key questions about the trade-offs between model size reduction and accuracy loss.
Unknown
This paper proposes a framework to harden LLM fine-tuning by combining differentially private data selection with trustworthiness-aware model quantization to enhance privacy and robustness.
Unknown
This paper introduces HIGGS, a novel quantization method for large language models that leverages the linearity theorem to push the limits of compression while preserving performance.
Unknown
QA-LoRA introduces a quantization-aware low-rank adaptation method that balances parameter efficiency and quantization robustness for fine-tuning large language models.