4 papers
Residual GRU+MHSA: A Lightweight Hybrid Recurrent Attention Model for Cardiovascular Disease Detection
Tejaswani Dash, Gautam Datla, Anudeep Vurity +5
Cardiovascular disease (CVD) remains the leading cause of mortality worldwide, underscoring the need for reliable and efficient predictive tools that support early intervention. Tr…
Polypersona: Persona-Grounded LLM for Synthetic Survey Responses
Tejaswani Dash, Dinesh Karri, Anudeep Vurity +4
This paper introduces PolyPersona, a generative framework for synthesizing persona-conditioned survey responses across multiple domains. The framework instruction-tunes compact cha…
Executable Governance for AI: Translating Policies into Rules Using LLMs
Gautam Varma Datla, Anudeep Vurity, Tejaswani Dash +3
AI policy guidance is predominantly written as prose, which practitioners must first convert into executable rules before frameworks can evaluate or enforce them. This manual step…
ColFigPhotoAttnNet: Reliable Finger Photo Presentation Attack Detection Leveraging Window-Attention on Color Spaces
Anudeep Vurity, Emanuela Marasco, Raghavendra Ramachandra +1
Finger photo Presentation Attack Detection (PAD) can significantly strengthen smartphone device security. However, these algorithms are trained to detect certain types of attacks.…