I'm Arnesh — a CS & AI undergraduate at IIIT Delhi. My research sits at the intersection of self-supervised learning, signal processing, and deep-learning theory & interpretability — published at NeurIPS, CVPR, TMLR, INTERSPEECH & ICMR.
My research lives at the intersection of self-supervised learning, signal processing, and deep-learning theory & interpretability — asking how networks build representations, what invariances they preserve, and where those representations quietly fail.
Ten works across journals, top-tier conferences and workshops. Asterisk (*) denotes equal contribution.
A theoretical & empirical study of what intermediate layers actually encode — reframing them as latent reservoirs of structure, and showing how to recover and exploit that signal for generalization. Accepted as a Spotlight at ICML 2026.
Working across academia and industry — from FAIR/Brown to medical-imaging labs at IIIT Delhi and startups building production-grade AI.
When I'm not reading papers or training models — I'm usually somewhere with a camera, a racquet, or a window seat.
Street, low-light, and long exposures. I shoot to train my eye on composition — the rule of thirds is basically attention.
Played since school. It's the one place I don't overthink — reaction, footwork, the satisfying click of a clean smash.
Somewhere between changing skylines and unfamiliar menus — most of my best ideas arrive on a train.