111 citations · 230 across the 35 of their papers we have counts for
38 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…
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…
Learning to Select Like Humans: Explainable Active Learning for Medical Imaging
Ifrat Ikhtear Uddin, Longwei Wang, Xiao Qin +2
Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by…
AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models
KC Santosh, Srikanth Baride, Rodrigue Rizk
As machine learning (ML) continues its rapid expansion, the environmental cost of model training and inference has become a critical societal concern. Existing benchmarks overwhelm…