Krishna Agaram

About

New: I’m looking for robotics internships at superfast startups; please find my resume here. I’ve got experience with vision, reinforcement learning, how to reduce the sim2real gap, and robot hardware.

Krishna at the canyon

Cedar Ridge,
the Grand Canyon, AZ

Hello! I’m Krishna Agaram, a grad student at UIUC advised by the amazing Prof. Saurabh Gupta. Previously, I was a CS undergrad at IIT Bombay. I enjoy robot learning and manipulation, reinforcement learning + theory, deep learning theory, pure math and cool dev projects.

I currently work on sim-to-real robot manipulation for long-horizon, contact-rich, precise bimanual tasks. In the past, I’ve worked on neural tangent kernels, reinforcement learning, property testing, probabilistic proofs and quantum information.

If I’m not trying to get reinforcement learning to work or doing some math, I’m likely reading Asimov or Christie, playing the piano, or outdoors on a run, hike or climb. I like entropy of all forms, so I’m always looking to learn new things and meet new people, so feel free to shoot me an email or connect on LinkedIn if there’s something you’d like to discuss!

Here’s my Resume, Github and LinkedIn. I sometimes make notes, which you can find here. I am a big supporter of inquiry-based learning; if you’re interested, I encourage checking out JIBLM. In the past, I wrote one such guide to Linear Algebra and a more elementary, story-book guide to Counting (draft). Finally, I have a kinda dead blog that needs more regular revival.

Publications

  • Quantum Advantage in Proof Systems without Entanglement
    K. Agaram, N. Spooner, Y. Zheng. Under review

  • Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems
    K. Agaram*, V. Kasprova*, A. Parulekar*, A. Alrabah*, R. Garg, S. Jha. Under review

  • Preparing arbitrary stabilizer states via disentangling and path-aware reinforcement learning
    K. Agaram*, S. Midha, V. Garg. QIP 2025 and ML4PS@NeurIPS 2025

  • Anti-concentration of the value of the XOR-monogamy-of-entanglement game
    K. Agaram. Draft available here.

Presentations

  • Quantum State Preparation with Reinforcement Learning
    Contributed talk, APS Global Physics Summit 2025 (talk, slides)

Coursework
  • UIUC: advanced NLP, computer vision, deep generative models, statistical RL theory
  • IITB, undergrad CS: data structures, algorithm analysis, logic, automata theory, cryptography, game theory and mechanism design, software systems, architecture, networks, operating systems, databases, compilers, advanced compilers, machine learning
  • IITB, grad CS: quantum information, spectral graph theory, approximation algorithms, randomized algorithms, probabilistic proofs, theoretical machine learning, statistical learning theory, theory of deep learning, formal methods in machine learning
  • IITB, math: linear algebra, probability and statistics, differential equations, calculus 1&2, real analysis, complex analysis, numerical analysis, fourier analysis, abstract algebra, extremal graph theory and graph colorings