AR

PhD Student in Computer Science, CU Boulder

Amit Kiran Rege

Hi! I am Amit Kiran Rege, a PhD student in Computer Science at the University of Colorado Boulder advised by Claire Monteleoni.

My research is in theoretical machine learning broadly construed, especially problems in AI safety and control. My recent focus is applying reinforcement learning theory to LLM post-training, while maintaining interests in foundational RL theory and the foundations of interpretability.

I am also interested in startups and early-stage venture through my role as an Associate at the Deming Center Venture Fund, where I help source and evaluate early-stage Colorado startups.

Outside work, I enjoy soccer, cricket, music, and following current affairs.

Updates

Quick highlights for talks, releases, paper milestones, and travel.

Mar 30, 2026

Lightning talk at Frontiers of Online Reinforcement Learning Workshop, IMSI

Talk title: "An Oracle Taxonomy for LM Post Training".

Mar 27, 2026

Defended PhD Thesis

Thesis title: "Structure and Reliability in Interactive Decision Making".

Feb 15, 2026

Attended ITA Workshop in San Diego

Presented our ongoing work on LLM reasoning.

View all updates

Publications

Featured papers with links to PDFs, code, slides, and project pages.

AISTATS - 2026

Multi-Agent Lipschitz Bandits

Amit Kiran Rege*, Sourav Chakraborty*, Claire Monteleoni, Lijun Chen

Accepted at the Twenty-Ninth International Conference on Artificial Intelligence and Statistics.

L4DC - 2026 ORAL

Flickering Multi-Armed Bandits

Amit Kiran Rege*, Sourav Chakraborty*, Claire Monteleoni, Lijun Chen

Accepted oral presentation at the 8th Annual Learning for Dynamics and Control Conference.

L4DC - 2026

A Unified Framework for Locality in Scalable MARL

Amit Kiran Rege*, Sourav Chakraborty*, Claire Monteleoni, Lijun Chen

Accepted at the 8th Annual Learning for Dynamics and Control Conference.

View all publications

Blog Posts

Long-form technical notes and research explainers.

Under Construction

New writing is in progress

Coming soon!

View all posts

Side Projects and Demos

Interactive prototypes and research engineering experiments.

Live Demo

RAGScope

Static retrieval debugger that shows where RAG failed: chunk split, metadata filter, or reranker regression. Each case includes gold support spans, counterfactual fixes, and answer claim audits.

JavaScriptGitHub PagesAstroJSON
Open Demo
View all demos

CV and Resume

Keep CV/Resume files in `public/assets/docs/` and update links in `src/data/profile.json`.