22 papers
Explainable Novel Category Discovery in Semantic Concept Space
Ifrat Ikhtear Uddin, Yang Zhou, KC Santosh +1
Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaqu…
GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring
Nicholas R. Rasmussen, Rodrigue Rizk, Longwei Wang +1
Deploying reliable bioacoustic monitoring systems requires models that generalize under high-noise, low-SNR conditions and evaluation protocols that expose deployment-relevant fail…
Advances and Challenges in Meta-Learning: A Technical Review
Anna Vettoruzzo, Mohamed-Rafik Bouguelia, Joaquin Vanschoren +2
Meta-learning empowers learning systems with the ability to acquire knowledge from multiple tasks, enabling faster adaptation and generalization to new tasks. This review provides…
Robust and Clinically Reliable EEG Biomarkers: A Cross Population Framework for Generalizable Parkinson's Disease Detection
Nicholas R. Rasmussen, Longwei Wang, Rodrigue Rizk +5
Developing robust and clinically reliable EEG biomarkers requires evaluation frameworks that explicitly address cross population generalization in multi site settings such as Parki…
Fragile Reasoning: A Mechanistic Analysis of LLM Sensitivity to Meaning-Preserving Perturbations
Shou-Tzu Han, Rodrigue Rizk, KC Santosh
Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systemati…
MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
Puskal Khadka, KC Santosh
State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains cha…