Sunil Gupta

SAPE-FL achieves superior model performance in heterogeneous environments by intelligently balancing global and local learning through similarity-aware personalization.

LLM-Detector achieves superior anomaly detection in tabular data without the need for fine-tuning, making it a game-changer for real-world applications.

LLMs can reason more accurately without extra compute: just intelligently reallocate your sampling budget based on a simple uncertainty estimate.