Shreyansh completed his MSc in Social Data Science and now works as a Research Assistant at the OII with a focus on evaluating safety and performative boundaries of AI models.
Prior to studying and working at the OII, Shreyansh completed his undergraduate degree in Data Science at CHRIST (Deemed to be University), India. During this time, he worked at startups and as a researcher on projects that involved building datasets and training computer vision models for agriculture, dentistry, and the entertainment industry.
Since his time at the OII, he has focused on Large Language Models (LLMs) and pushing their boundaries in constrained environments. His dissertation focused on understanding adversarial safety capabilities that develop during knowledge and dataset distillation in LLMs. He currently works on benchmarking and engineering projects with agentic and multimodal LLMs.
Computer Vision, LLMs, Knowledge Distillation, AI Safety, AI & Healthcare
25 November 2025
Researchers from the Oxford Internet Institute at the University of Oxford will be at NeurIPS 2025 in San Diego from 1- 7 December, 2025, contributing to one of the world’s leading AI conferences.
