Sai Suresh Macharla Vasu

About Me

I am an M.Sc. student in Data Science and Artificial Intelligence (DSAI) at Saarland University, Germany. I am currently a Student Research Assistant in the Trustworthy ML group at CISPA Helmholtz Center for Information Security, in the group of Prof. Dr. Mario Fritz. I am also a Research Fellow in the Fall 2026 cohort of SPAR (Supervised Program for Alignment Research), where I work on moral shadowbanning — whether conversational AI provides systematically different levels of helpfulness, honesty, or harmlessness to users perceived as having poor moral character. I was a Research Fellow at the AI Safety Saarland Incubator and a Student Research Assistant at DFKI in the Interactive Machine Learning group.

Research Interests

• AI Safety and Evaluation: Understanding failure modes, biases, and safety risks in language models and autonomous AI agents.
• Contextual Integrity and Agent Safety: Studying how AI agents should use and share information appropriately across different contexts, including privacy and changing user permissions.
• Long-Term Memory and Personalization: Exploring how agents maintain, update, and retrieve personal information over extended interactions, including conflicting or outdated memories.
• Human–AI Interaction: Understanding how AI systems influence users and how their behavior can be evaluated in realistic, long-term settings.

News

• [Sep. 2026] Selected as a Research Fellow in the Fall 2026 cohort of SPAR (Supervised Program for Alignment Research).
• [Jul. 2026] Served as a Student Volunteer at ACL 2026 in San Diego, USA.
• [Jul. 2026] Reviewing for the NeurIPS 2026 Evaluations & Datasets Track.
• [Apr. 2026] Paper “Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews” accepted to ACL 2026 Findings.
• [Apr. 2026] Awarded the Saarland Scholarship for International Students (Summer Semester 2026).
• [Feb. 2026] Paper “Challenges of Evaluating LLM Safety for User Welfare” accepted to IASEAI’26.
• [Dec. 2025] Started as Student Research Assistant at CISPA Helmholtz Center for Information Security (Trustworthy ML group).
• [Nov. 2025] Paper “Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews” presented at NeurIPS 2025 Workshop on LLM Evaluation.
• [Nov. 2025] Paper “AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping” presented at NeurIPS 2025 Workshop on Generative AI in Finance.
• [Oct. 2025] Selected as Research Fellow at the AI Safety Saarland Incubator.
• [Jul. 2025] Awarded the Saarland Scholarship for International Students (Summer Semester 2025).

Publications

Beyond Research

I am an avid traveller — having explored 15+ countries across the world. Outside of academia, I enjoy staying updated on the latest in tech and culture through X, and I am a big movie buff.

I am also a proud President Scout Awardee, having received the highest scouting honour in India from the Former President of India in December 2016.

Powered by Jekyll and Minimal Light theme.