4 papers · 1 filter
PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces
M. Yigit Turali, Shreyas Rajesh, M. Efe Lorasdagi +3
Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigations grow, agents…
BLInD: Learning Driver Intent as a Distribution over Future Ego Trajectories
Flavian Pegado, Ronit Hire, Shreyas Rajesh +1
We present BLInD (Blind Learned Intent Distribution), a compact network that maps recent vehicle-state history (e.g. speed, curvature, indicator, and vehicle type) to a top-k distr…
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
Shreyas Rajesh, Kartik Sharma, Tonmoy Monsoor +8
Specialist epilepsy expertise is scarce in resource-constrained settings. Clinical decision-support systems must adapt to local prescribing practices and recognize when specialist…
Panini: Continual Learning in Token Space via Structured Memory
Shreyas Rajesh, Pavan Holur, Mehmet Yigit Turali +2
Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retri…