Assistant Professor Dr. Ajaz Ahmad Bhat delivered an insightful talk titled “From Code to Creation” at Universiti Brunei Darussalam.
Event: 2025 CHINA (GUANGXI) – ASEAN Vocational Education and Development Conference on “Artificial Intelligence + Advanced Manufacturing” Talk: Applied-AI &...
Glad to share Haji Gul from my lab, working under my and Dr. Ghani’s supervision, has been selected as a...
Event: Artificial Intelligence (AI) Education and Awareness Seminar Talk: AI in Defence — From Awareness to Operational Advantage Venue: SHHBIDSS...
Vacancies are available for local and international candidates interested in pursuing a Master’s or PhD degree in our lab. Our...
Visual exploration and auditory processing interact to support object discrimination, categorization, and early word learning. To clarify their complex, multi‐timescale interactions, we generalize a formal neural process model of word learning to simulate two infant studies of label‐driven novelty preference (9–22 months).
Context manipulations reveal that similarity in object properties can counterintuitively facilitate word learning. Using the WOLVES dynamic field model, we simulated CSWL under two conditions: 'NEAR' (objects metrically similar) and 'FAR' (objects distinct). WOLVES predicted superior learning in NEAR trials. An adult behavioral experiment confirmed this novel prediction, demonstrating that contextual similarity enhances cross‐situational word mapping.
Current evaluation practices for knowledge graph completion models lack standardization and often fail to capture model capabilities comprehensively. We introduce KG-EDAS (Knowledge Graph Evaluation through Data-Aware Scoring), a meta-metric framework that provides more robust and interpretable evaluation of KGC models.
We propose MuCo-KGC, a multi-context-aware approach that leverages diverse contextual signals to improve link prediction performance. Our method achieves state-of-the-art results on several benchmarks while maintaining computational efficiency.
We introduce MuCoS (*Multi-Context-Aware Sampling*), a novel approach that efficiently discovers drug targets by sampling diverse contextual neighborhoods in biomedical KGs. Our method significantly improves target identification accuracy while reducing computational overhead.