4 papers
Bayesian Fine-tuning in Projected Subspaces
Viktar Dubovik, Patryk MarszaÅek, Jacek Tabor +1
Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of large models by decomposing weight updates into low-rank matrices, significantly reducing storage and computat…
TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference
Patryk MarszaÅek, Tomasz KuÅmierczyk, Marek Åmieja
Anomaly detection for tabular data has been a long-standing unsupervised learning problem that remains a major challenge for current deep learning models. Recently, in-context lear…
ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
Patryk MarszaÅek, Tomasz KuÅmierczyk, Witold WydmaÅski +2
Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across da…
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
Patryk MarszaÅek, Klaudia BaÅazy, Jacek Tabor +1
Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of large language models by decomposing weight updates into low-rank matrices, significantly reducing storage and…