Publications

Are We Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs

SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code

Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection

Fighting Sampling Bias: A Framework for Training and Evaluating Credit Scoring Models

Probabilistic Demand Forecasting with Graph Neural Networks

Recency: Prediction with a Single Data Point