5 papers
UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space
Amir Mohammad Ezzati, Kiyan Rezaee, Bardiya Kariminia +4
Large vision--language models (LVLMs) demonstrate strong multimodal reasoning capabilities but remain prone to hallucination, where model predictions are not grounded in visual evi…
SCPP: A Unified Python Library for Soft Clustering
Kiyan Rezaee, Morteza Ziabakhsh, Artin Bahrampour +6
In this paper, we present SCPP (Soft Clustering Python Package), an open-source Python framework for soft clustering. SCPP establishes a canonical, scikit-learn-compatible estimato…
FOS: A Large-Scale Temporal Graph Benchmark for Scientific Interdisciplinary Link Prediction
Kiyan Rezaee, Morteza Ziabakhsh, Niloofar Nikfarjam +4
Interdisciplinary scientific breakthroughs mostly emerge unexpectedly, and forecasting the formation of novel research fields remains a major challenge. We introduce FOS (Future Of…
Extracting Overlapping Microservices from Monolithic Code via Deep Semantic Embeddings and Graph Neural Network-Based Soft Clustering
Morteza Ziabakhsh, Kiyan Rezaee, Sadegh Eskandari +2
Modern software systems are increasingly shifting from monolithic architectures to microservices to enhance scalability, maintainability, and deployment flexibility. Existing micro…
Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks
Seyed Amir Bidaki, Amir Mohammadkhah, Kiyan Rezaee +4
Online Continual Learning (OCL) is a critical area in machine learning, focusing on enabling models to adapt to evolving data streams in real-time while addressing challenges such…