6 papers
Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Model
Renjith Prasad, Chathurangi Shyalika, Anushka Pawar +2
Multimodal generative models produce fluent outputs but remain unreliable when generation must respect structured, domain-specific, or safety-critical knowledge. Existing methods i…
Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena
Renjith Prasad, Rishabh Sharma, Andrew E. Shao +8
Subtle visual anomalies such as hairline cracks, sub-millimeter voids, and low-contrast inclusions are structurally atypical yet visually ambiguous, making them both difficult to a…
DETONATE: A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization
Renjith Prasad, Abhilekh Borah, Hasnat Md Abdullah +9
Alignment is crucial for text-to-image (T2I) models to ensure that generated images faithfully capture user intent while maintaining safety and fairness. Direct Preference Optimiza…
SmartPilot: A Multiagent CoPilot for Adaptive and Intelligent Manufacturing
Chathurangi Shyalika, Renjith Prasad, Alaa Al Ghazo +4
In the dynamic landscape of Industry 4.0, achieving efficiency, precision, and adaptability is essential to optimize manufacturing operations. Industries suffer due to supply chain…
NSF-MAP: Neurosymbolic Multimodal Fusion for Robust and Interpretable Anomaly Prediction in Assembly Pipelines
Chathurangi Shyalika, Renjith Prasad, Fadi El Kalach +4
In modern assembly pipelines, identifying anomalies is crucial in ensuring product quality and operational efficiency. Conventional single-modality methods fail to capture the intr…
Time Series Foundational Models: Their Role in Anomaly Detection and Prediction
Chathurangi Shyalika, Harleen Kaur Bagga, Ahan Bhatt +3
Time series foundational models (TSFM) have gained prominence in time series forecasting, promising state-of-the-art performance across various applications. However, their applica…