Viewing profile — bgavran

There is an existing implementation validating this idea, and the plan is to make it publicly available at some point. > It seems to me that such an idea would be workable on a giv…

There's been some exciting work generalising transformers to data structures that aren't just pure arrays: https://glaive-research.org/2025/02/11/Generalized-Transform... I've impl…

Author here - thanks for engaging. > One way to think of the bitter lesson as it applies to generative models is that ~all data carries some information about the structure of real…

A coproduct in the category Set is a disjoint union of sets, i.e. A + B + C where A, B, C are sets. We can think of this coproduct as involving two choices: 1) a choice of which co…

Author here - thanks for engaging. On existing techniques - Type-Constrained Generation paper is discussed in the blog post (under Constrained Decoding), and I'd group typed holes …

This is an interesting writeup, I wonder if the authors considered a categorical approach to representation of general applicative arrays (which might be tree-shaped), as described…

Indeed, the author seems to have a misunderstanding about both undecidability and complexity as they pertain to dependent types. Dependent types do not add complexity to our system…

"Anybody can share a sucess story of using a car to go places I couldn't have gone on foot"? CT is a language and a tool, meaning anything you can say in the language of CT you can…

There's a well-articulated essay from Christopher Olah that captures the undercurrent, and perhaps even the motivation of many of these papers https://colah.github.io/posts/2015-09…

It's also meant to suggest where things are going (the kind of a chart I have in mind is this one https://twitter.com/bgavran3/status/1422206118688956420 ), though I understand thi…

OP here. The exponential growth in CS publication is much faster. This repository is simply a testament that CT is slowly ramping up. It's meant to show what kind of expressive pow…