Selfbyt is a small research group working on computing systems and machine learning.

We publish papers and notes, share code where we can, and build a few internal tools that we use ourselves. The site is the archive of that work.

• i.

  Measurements over manifestos

  Concrete numbers, reproducible setups, and code people can actually run. Claims that aren't measurable get cut.

• ii.

  Systems and learning together

  We work where the algorithms meet the hardware. Inference paths, memory layout, and model structure are studied as one thing, not three.

• iii.

  Open notes, when we can

  We share method notes, scripts, and partial results — not just polished papers. Some work stays internal while it's still rough.

• iv.

  Small on purpose

  We stay small so we can focus. Fewer people, fewer meetings, more time on the actual problem.

• Research

  Papers, technical reports, and reproducible experiments on inference, sparsity, and evaluation.

  Read research→

• Writing

  Method notes, post-mortems, and shorter pieces about what we're working on right now.

  Browse writing→

• Software

  Internal tools we use day to day. Some get released; some stay in-house while we harden them.

  Ask about access→