10 papers
Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI Agents
Santosh Patapati
Modern web interfaces are increasingly difficult to use with screen readers, particularly when pages update dynamically or hide important structure behind visual layout. Recent UI…
Graph Coloring for Multi-Task Learning
Santosh Patapati, Ian Noronha
When different objectives conflict with each other in multi-task learning, gradients begin to interfere and slow convergence, thereby potentially reducing the final model's perform…
Vision-Language Cross-Attention for Real-Time Autonomous Driving
Santosh Patapati, Trisanth Srinivasan, Murari Ambati
Autonomous cars need geometric accuracy and semantic understanding to navigate complex environments, yet most stacks handle them separately. We present XYZ-Drive, a single vision-l…
Goal-Based Vision-Language Driving
Santosh Patapati, Trisanth Srinivasan
Autonomous vehicles must react in milliseconds while reasoning about road geometry and traffic intent to navigate complex situations. We introduce NovaDrive, a single-branch vision…
Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
Trisanth Srinivasan, Santosh Patapati
This paper introduces Democracy-in-Silico, an agent-based simulation where societies of advanced AI agents, imbued with complex psychological personas, govern themselves under diff…
WebNav: An Intelligent Agent for Voice-Controlled Web Navigation
Trisanth Srinivasan, Santosh Patapati
The current state of modern web interfaces, especially in regards to accessibility focused usage is extremely lacking. Traditional methods for web interaction, such as scripting la…