4 papers
Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs
Shahzeb Qamar, Lorenz Sparrenberg, Christian Bauckhage +5
Deployment of Large Language Models (LLMs) on memory-constrained edge devices relies heavily on aggressive post-training quantization. However, evaluating these models is largely b…
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg +4
Post-Training Quantization has become widely used to compress large language models to make them deployable on resource-constrained devices. However, the evaluation of quantization…
MolGraph-xLSTM: A graph-based dual-level xLSTM framework with multi-head mixture-of-experts for enhanced molecular representation and interpretability
Yan Sun, Yutong Lu, Yan Yi Li +3
Predicting molecular properties is essential for drug discovery, and computational methods can greatly enhance this process. Molecular graphs have become a focus for representation…
Hyperedge Anomaly Detection with Hypergraph Neural Network
Md. Tanvir Alam, Md. Mahmudur Rahman, Md. Fahim Arefin +4
Hypergraph is a data structure that enables us to model higher-order associations among data entities. Conventional graph-structured data can represent pairwise relationships only,…