How can a system change
without losing what matters?

I’m Navish Kumar, a machine-learning researcher at the University of Basel.

I study how learning systems change—and build tools that make that change inspectable.

Follow the work

A body of work, in motion.

Scroll through the work. Enter an idea to follow it further.

2020–2025

PastFoundations

From relationships in networks to the geometry of learning.

  1. 2020 · Published research

    Interaction dynamics

    Look at who replies to whom—not just how much each group posts.

    Enter the idea
  2. 2021 · Published · Linear Algebra and its Applications

    Extremal spectral bounds

    Turn a spectral warning into a lower bound on structural repair.

    Enter the idea
  3. 2022 · Published · American Journal of Combinatorics

    Normalized gain Laplacians

    Change one relationship. Watch the inconsistency enter the spectrum.

    Enter the idea
  4. 2022–2023 · NeurIPS 2022 workshop · 2023 preprint

    Urban micro-regions

    Change the street context. See parking, travel and walking add up.

    Enter the idea
  5. 2025 · Preprint

    Natural-gradient guarantees

    Fit a distribution, not just a point—and expose the update geometry.

    Enter the idea
2026

NowActive work

What should change, what should stay, and who gets to decide?

  1. 2026 · Active research

    Experience Replay

    Learn something new. Lose an old skill. Choose the missing correction.

    Enter the idea
  2. 2026 · Active research

    Rank Feasibility

    Increase the available rank. Separate possible from affordable.

    Enter the idea
  3. 2026 · Replication / ongoing investigation

    TiC-LM replication

    Advance time. Watch the same historical data become stale.

    Enter the idea
  4. 2026 · System in development

    CasePath

    Find the contradiction. Refuse the action. Correct only what depends on it.

    Enter the idea
Looking ahead

FrontierDirection

Intelligence that can act in a world we can inspect and revise.

  1. Frontier · Working interface prototype · research direction

    GenAI × spatial computing

    Create a laboratory. Move one object. Keep the rest of the world.

    Enter the idea

Let’s talk

An idea worth understanding.
A system worth building.

navish.kumar@unibas.ch

Research, collaboration, and difficult questions welcome.