5 papers
SGHA: Evidence-Grounded Research Problem Discovery with Local Language Models
Sarvesh Gharat, Junpei Komiyama
Recent efforts toward fully automated AI scientists have demonstrated that language-model agents can generate hypotheses, execute experiments, and draft scientific manuscripts. How…
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
Vaibhav Singh, Soumya Suvra Ghosal, Sarvesh Gharat +3
Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies reveal th…
Beyond Listenership: AI-Predicted Interventions Drive Improvements in Maternal Health Behaviours
Arpan Dasgupta, Sarvesh Gharat, Neha Madhiwalla +3
Automated voice calls with health information are a proven method for disseminating maternal and child health information among beneficiaries and are deployed in several programs a…
Representative Arm Identification: A fixed confidence approach to identify cluster representatives
Sarvesh Gharat, Aniket Yadav, Nikhil Karamchandani +1
We study the representative arm identification (RAI) problem in the multi-armed bandits (MAB) framework, wherein we have a collection of arms, each associated with an unknown rewar…
Gamma Ray AGNs: Estimating Redshifts and Blazar Classification using traditional Neural Networks with smart initialization and self-supervised learning
Sarvesh Gharat, Abhimanyu Borthakur, Gopal Bhatta
Redshift estimation and the classification of gamma-ray AGNs represent crucial challenges in the field of gamma-ray astronomy. Recent efforts have been made to tackle these problem…