10 papers
MolFM-Lite: Multi-Modal Molecular Property Prediction with Conformer Ensemble Attention and Cross-Modal Fusion
Syed Omer Shah, Mohammed Maqsood Ahmed, Danish Mohiuddin Mohammed +2
Most machine learning models for molecular property prediction rely on a single molecular representation (either a sequence, a graph, or a 3D structure) and treat molecular geometr…
LAF-YOLOv10 with Partial Convolution Backbone, Attention-Guided Feature Pyramid, Auxiliary P2 Head, and Wise-IoU Loss for Small Object Detection in Drone Aerial Imagery
Sohail Ali Farooqui, Zuhair Ahmed Khan Taha, Mohammed Mudassir Uddin +1
Unmanned aerial vehicles serve as primary sensing platforms for surveillance, traffic monitoring, and disaster response, making aerial object detection a central problem in applied…
Privacy-Preserving Federated Learning with Verifiable Fairness Guarantees
Mohammed Himayath Ali, Mohammed Aqib Abdullah, Syed Muneer Hussain +2
Federated learning enables collaborative model training across distributed institutions without centralizing sensitive data; however, ensuring algorithmic fairness across heterogen…
Constraint-Aware Neurosymbolic Uncertainty Quantification with Bayesian Deep Learning for Scientific Discovery
Shahnawaz Alam, Mohammed Mudassir Uddin, Mohammed Kaif Pasha
Scientific Artificial Intelligence (AI) applications require models that deliver trustworthy uncertainty estimates while respecting domain constraints. Existing uncertainty quantif…
DriftGuard: A Hierarchical Framework for Concept Drift Detection and Remediation in Supply Chain Forecasting
Shahnawaz Alam, Mohammed Abdul Rahman, Bareera Sadeqa
Supply chain forecasting models degrade over time as real-world conditions change. Promotions shift, consumer preferences evolve, and supply disruptions alter demand patterns, caus…
SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations
Mohammed Himayath Ali, Mohammed Aqib Abdullah, Mohammed Mudassir Uddin +1
Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, depl…
AgentCompress: Task-Aware Compression for Affordable Large Language Model Agents
Zuhair Ahmed Khan Taha, Mohammed Mudassir Uddin, Shahnawaz Alam
Large language models hold considerable promise for various applications, but their computational requirements create a barrier that many institutions cannot overcome. A single ses…
Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition
Mohammed Mudassir Uddin, Shahnawaz Alam, Mohammed Kaif Pasha
Extracting sparse circuits from billion-parameter transformers is constrained by search cost and pervasive feature reuse across co-active pathways. Hierarchical Attributio…
Meta-Learning Guided Pruning for Few-Shot Plant Pathology on Edge Devices
Mohammed Mudassir Uddin, Shahnawaz Alam, Mohammed Kaif Pasha +3
Farmers in remote areas need quick and reliable methods for identifying plant diseases, yet they often lack access to laboratories or high-performance computing resources. Deep lea…
Cost-effective Deep Learning Infrastructure with NVIDIA GPU
Aatiz Ghimire, Shahnawaz Alam, Siman Giri +1
The growing demand for computational power is driven by advancements in deep learning, the increasing need for big data processing, and the requirements of scientific simulations f…