Adrian Hill
@adrianhill.de
PhD student at @bifold.berlin, Machine Learning Group, TU Berlin. Automatic Differentiation, Explainable AI and #JuliaLang. Open source person: adrianhill.de
A 'side project' of mine just got published in ChemTexts! (linked in last post) 1/3 I always really loved etymology and figuring out where certain words come from. The names of chemical elements are particularly interesting, as meaning, phonetics and societal stuff gets mashed together.
Update: this guy has been revived as a ~stateless NixOS machine with impermanence wipes on every boot. It has a scoped GitHub access token for my bot-account "Bdrian" and I ssh into it to --dangerously-skip-permissions.
Adrian Hill@adrianhill.de · 5mo agoThrowback to my first macBook in 2018
Fantastic talk by @npreining.bsky.social and a great look behind the scenes of the arXiv!
Typst@typst.app · 5mo agoDid you know that arXiv is exploring to add Typst? The world's largest preprint archive faces unique challenges to keep science open. Join arXiv veteran Norbert Preining and learn what's ahead for arXiv and Typst. www.youtube.com/watch?v=zNZl...
chardet was vipeforked to MIT and I have thoughts about it. Spoiler: I like it. lucumr.pocoo.org/2026/3/5/the...
AI And The Ship of Theseus
Slopforks: what happens when a library gets rewritten with AI?
lucumr.pocoo.org
Yes, all the papers I have to review have the same honeypot. Glad I didn't flag the first one.
Adrian Hill@adrianhill.de · 5mo agoWasted half a day on a prompt injection attack in one of the papers I had to review, only to find out that it was probably the conference organizers who put it there (?)
Wasted half a day on a prompt injection attack in one of the papers I had to review, only to find out that it was probably the conference organizers who put it there (?)
🏆Award-winning: France's Prix Science Ouverte 2025 Switching AD backends in Julia used to mean rewriting your whole codebase. @gdalle.bsky.social @adrianhill.de got fed up — and built #DI instead. News: t1p.de/58a65 @julialang.org @ecoledesponts.bsky.social #julialang @tuberlin.bsky.social
Open-Source Award for DifferentiationInterface.jl
DifferentiationInterface.jl, co-developed by BIFOLD researcher Adrian Hill, wins one of France’s Open Science Awards for making cutting-edge modeling and optimization more flexible, efficient, and ope...
t1p.de
Yesterday, my puzzle book Workworkwork won the Thinky Award for the Best Pen and Paper Puzzle ( @thinkygames.com )! In celebration I added 100 free community copies of the digital (PDF) version: letibus.itch.io/www Check out more about the game / get the physical copy here: blazgracar.com/www
Claude Code vs. the editor-industrial-complex, who will come out on top?
marcel ⊙@marceldotsci.bsky.social · 7mo agomy long bet to not bother to learn vim commands has finally paid off #sloperator
„Making things easy breaks systems that use difficulty as signaling“ @zey.bsky.social @neuripsconf.bsky.social
Adrian Hill@adrianhill.de · 9mo agoTechnical issues aside, it seems that the signal-to-noise ratio on both sides of the review process has reached a critical low point. And the academic community hasn’t yet figured out how to deal with this.
Join us today from 4:30 to 7:30 PM @neuripsconf.bsky.social Hall C,D,E #1006 for our poster on SmoothDiff, a novel XAI method leveraging automatic differentiation. 🧵1/6
In San Diego for @neuripsconf.bsky.social this week, so hit me up to talk science. I'll make one of these longer announcement posts for our paper on Wednesday.
Awesome to see the French government recognize our work on open-source software! @ouvrirlascience.bsky.social
Guillaume Dalle@gdalle.bsky.social · 8mo agoMy baby #JuliaLang package got an award! DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month. Research != just papers.
When it comes to drama, ICLR 2026 is truly the gift that keeps on giving.
If I were looking for a PhD position, I'd jump at this chance!
Guillaume Dalle@gdalle.bsky.social · 9mo ago⚠️ WANTED: PhD student ⚠️ The topic? GPU-friendly algorithms for discrete optimization and mathematical programming, to be used inside decision-focused learning pipelines. The mentors? My colleague Axel Parmentier and myself. [1/3]
Working on a poster in Typst again. But this time from scratch without any package dependency. 💪
![Proof of concept for a Typst poster with a two-column layout and the entire code that produces it:
```typst
// Poster Template
#set page("a0", flipped: true,
columns: 2,
margin: 3cm,
background: rect(fill: blue, width: 100%, height: 100%),
)
#set columns(gutter: 2cm)
#set par(spacing: 2cm)
#set text(font: "Helvetica", size: 90pt)
#set rect(width: 100%, inset: 1cm, fill: white)
// Content
#place(top, scope: "parent", float: true, clearance: 2cm,
rect(height: 8cm)[Title],
)
#rect(height: 1fr)[Panel 1]
#rect(height: 1fr)[Panel 2]
#rect(height: 1fr)[Panel 3]
#colbreak()
#rect(height: 3fr)[Panel 4]
#rect(height: 2fr)[Panel 5]
#place(bottom, scope: "parent", float: true, clearance: 2cm,
rect(height: 5cm)[Footer],
)
```](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:itr23nhumbwtts2cwfcoj747/bafkreiak5x5jbtq634oinzjb4dwolnjw6xyfxoavdfdk5gqa7lmjojn2ye)
This is the eXplainable AI research channel of the machine learning group of Prof. Klaus-Robert Müller at Technische Universität Berlin @tuberlin.bsky.social & BIFOLD @bifold.berlin. Let's connect! #XAI #ExplainableAI #MechInterp #MachineLearning #Interpretability
a black background with green text that says `` hello , world ''
ALT: a black background with green text that says `` hello , world ''
media.tenor.com
Microtypography, accessibility and a range of PDF standards. Now nothing is stopping me from writing my thesis in Typst. 🥹
Typst@typst.app · 10mo agoTypst 0.14 is out now! Get ready for production with accessibility, PDFs as images, character-level justification, and more. Learn about more of the highlights in Typst 0.14 in the thread below ⤵️
This might actually motivate me to follow through AoC this year! Maybe in Typst?
Eric Wastl@was.tl · 10mo agoHello, friends! After 10(!) years of #AdventOfCode, I've made some changes to preserve my sanity: there will be 12 days of puzzles each December (still starting Dec 1) and there is no longer a global leaderboard. Read more: adventofcode.com/2025/about#f... adventofcode.com/2025/about#f...
Turns out NLP is just vision
mr. TIM@timkellogg.me · 10mo agoZ.ai released a paper very similar to DeepSeek-OCR on the same exact day (a few hours earlier afaict) Glyph is just a framework, not a model, but they got Qwen3-8B (128k context) to handle over 1 million context by rendering input as images arxiv.org/abs/2510.17800
Curious what you can do with Typst's HTML export right now? How about write a blog? This article tells you how: blog.sillyfreak.space/2025/06/29/r...
Rewrite it (the Blog) in Typst
Rewrite it (the Blog) in Typst
blog.sillyfreak.space
Kind of hilarious that functional programming's biggest hit is a package manager
Perfect timing! If you are in Paris for @juliacon.bsky.social on Friday, join us for our talk on Automatic Sparse Differentiation at 11:30. If you can't make it, check out both the paper and our introductory ICLR blog post: iclr-blogposts.github.io/2025/blog/sp...
An Illustrated Guide to Automatic Sparse Differentiation | ICLR Blogposts 2025
In numerous applications of machine learning, Hessians and Jacobians exhibit sparsity, a property that can be leveraged to vastly accelerate their computation. While the usage of automatic differentia...
iclr-blogposts.github.io
TMLR Published Papers@tmlr-pub.bsky.social · 11mo agoSparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation Adrian Hill, Guillaume Dalle Action editor: Pierre Ablin https://openreview.net/forum?id=GtXSN52nIW #sparser #sparse #hessians