Research

I use independent research to explore ideas that feel important before their product shape is obvious. Lately, I have been asking how multimodal systems should represent space, time, and long context, and what architectures might move beyond today's dominant recipes.

I publish code, artifacts, experimental details, and the paths that did not work. The aim is to leave behind something another person can inspect, reproduce, or build upon.

Questions I'm exploring

Current experiments

2026

A Little RoPE Goes a Long Way

One question I keep coming back to is whether the architectural choices inherited from language are right for vision. This project tests rotation as an inductive bias for contrastive vision-language encoders. The experiments study when 2D RoPE helps, when it does not, and whether the same idea can extend context without retraining.

the write-up · code & experiments

Papers and software

Talks

More on the videos page.