Bhagyesh Kumar
(@invi-bhagyesh)

I am currently a sophomore in the Department of Mathematics at MIT Manipal , majoring in Mathematics and Computing. I am part of the SPAR Spring 2026 cohort, where I am working on emergent misalignment under Prof. Lionel Levine from Cornell University. I am also working on evaluation awareness as an AI safety researcher at Algoverse under Jord Nguyen. In addition, I am a member of the MRM Research AI Team where I was mentored by A S Aravinthakshan.

I have previously worked on adversarial attacks, which led to my interest in trustworthy machine learning. Overall, my research interest lies in AI safety and Trustworthy AI. See my research and what I'm up to now.

Other things I enjoy include competitive programming, reading blogs, and meeting new people. Feel free to reach out and say hi at (invi.bhagyesh@gmail.com), though I usually respond faster on social apps.

publications