الباحثون

Sumit Negi

المنشورات 2

نسخة أولية وصول مفتوح

Same Text, Different Prediction: Serving-Context Nondeterminism in Text Classifiers

Deterministic inference is essential for reliable and trustworthy machine learning. Prior studies of text generation have shown that changing factors such as batch size, batch composition, hardware, or inference engine can alter the generated text, even when the prompt, model parameters, and sampling randomness are fix …

نسخة أولية وصول مفتوح

Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion

Kevin Zhai, Siva Rajesh Kasa, Soumya Roy وآخرون · 2026

Text-to-image generation enables users to explore several images generated from the same prompt. For these generated images to be useful, each one must reflect the user's preferences, measured by a learned reward, and differ visually from the others to maintain diversity. Existing methods are limited: they either addre …

المؤلفون المشاركون