Adrian Hill @ NeurIPS San Diego
LightNews LightNews
banner
adrianhill.de
Adrian Hill @ NeurIPS San Diego
@adrianhill.de
700 followers 590 following 110 posts
PhD student at @bifold.berlin, Machine Learning Group, TU Berlin.
Automatic Differentiation, Explainable AI and #JuliaLang.
Open source person: adrianhill.de/projects
Posts Replies Media Videos
Pinned
adrianhill.de
Adrian Hill @ NeurIPS San Diego @adrianhill.de · Jan 30
You think Jacobian and Hessian matrices are prohibitively expensive to compute on your problem? Our latest preprint with @gdalle.bsky.social might change your mind!
arxiv.org/abs/2501.17737
🧵1/8
Figure comparing automatic differentiation (AD) and automatic sparse differentiation (ASD). (a) Given a function f, AD backends return a function computing vector-Jacobian products (VJPs). (b) Standard AD computes Jacobians row-by-row by evaluating VJPs with all standard basis vectors. (c) ASD reduces the number of VJP evaluations by first detecting a sparsity pattern of non-zero values, coloring orthogonal rows in the pattern and simultaneously evaluating VJPs of orthogonal rows. The concepts shown in this figure directly translate to forward-mode, which computes Jacobians column-by-column instead of row-by-row.
adrianhill.de
„Making things easy breaks systems that use difficulty as signaling“ @zey.bsky.social @neuripsconf.bsky.social
December 3, 2025 at 11:10 PM
adrianhill.de
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
December 3, 2025 at 7:36 PM
adrianhill.de
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.
December 2, 2025 at 7:05 PM
adrianhill.de
Awesome to see the French government recognize our work on open-source software! @ouvrirlascience.bsky.social
gdalle.bsky.social Guillaume Dalle @gdalle.bsky.social · 24d
My 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.
A close up of the trophy for the "prix science ouverte du logiciel libre de recherche, édition 2025" (open science prize for free research software, 2025 edition)
December 2, 2025 at 7:03 PM
adrianhill.de
When it comes to drama, ICLR 2026 is truly the gift that keeps on giving.
November 28, 2025 at 7:17 AM
adrianhill.de
If I were looking for a PhD position, I'd jump at this chance!
gdalle.bsky.social Guillaume Dalle @gdalle.bsky.social · Nov 21
⚠️ 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]
November 21, 2025 at 5:55 PM
adrianhill.de
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], ) ```
November 3, 2025 at 8:52 PM
Reposted by Adrian Hill @ NeurIPS San Diego
xai-berlin.bsky.social
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
November 3, 2025 at 11:43 AM
Reposted by Adrian Hill @ NeurIPS San Diego
jeremykun.com
Mastodon came through, gotta up your game mathsky 😘
jeremykun.com Jeremy Kun @jeremykun.com · Oct 30
Look at me I'm posting an image from another social network like a basic bitch.

But THAT social network has typesetting 😀 and so the post reads nicer than if I retyped it here with no typesetting.
A math problem showed up organically in some work stuff: Given a graph G you'd like to produce a subgraph G prime. G comes with a partition of vertices V1 through Vk with the constraint that, for each subset Vi, at least one vertex in Vi must remain in the final graph. The goal is to make G' colorable with as few colors as possible. Anyone heard of something like this? It is almost surely NP-hard, but just curious.
October 31, 2025 at 1:48 AM
adrianhill.de
Microtypography, accessibility and a range of PDF standards. Now nothing is stopping me from writing my thesis in Typst. 🥹
typst.app Typst @typst.app · Oct 24
Typst 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 ⤵️
Image saying Typst 0.14. It has a holographic effect. The background is a pattern of checkmarks, at the top, it changes to a pattern of the string "0.14". The horizontal bar across the top reads "Title Elementm Skewed Fractions, Table Subheaders, Accessible Documents, Character-level Justification, PDF/A compliance, PDF Images, Typed HTML API"
October 24, 2025 at 1:51 PM
adrianhill.de
This might actually motivate me to follow through AoC this year! Maybe in Typst?
was.tl Eric Wastl @was.tl · Oct 22
Hello, 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...
October 23, 2025 at 1:15 PM
Reposted by Adrian Hill @ NeurIPS San Diego
bokmangeorg.bsky.social
Turns out NLP is just vision
timkellogg.me Tim Kellogg @timkellogg.me · Oct 21
Z.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
Figure 1. (Upper) Diagram comparing two paradigms for long-context tasks: • Left path (Plain Text): A long novel (~180K words, example “Jane Eyre”) is fed directly as text into an LLM, requiring roughly 240K tokens. • Right path (Rendering): The same text is rendered into images, producing about 80K tokens—achieving 3× input-token compression—and processed by a VLM (Vision-Language Model) instead of a pure text LLM. (Lower) Two sets of bar charts: • Left chart (Accuracy): Glyph performs comparably to Qwen-3-8B, GLM-4.9B-Chat-1M, and Qwen-2.5-7B-Instruct-1M on LongBench and MRCR tasks. • Right chart (Compression/Speedup): Glyph shows 3.2× KV cache reduction, 4.8× prefill speedup, and 4.4× decoding throughput compared to the text backbone model. Caption text: Comparison of two paradigms for long-context tasks: conventional approaches directly feeding plain text into LLMs, and the proposed VLM-based paradigm, Glyph, which renders text as compact images to achieve substantial input-token compression. Glyph attains competitive performance on LongBench and MRCR while offering significant compression and inference speedup over its text backbone model on 128K-token inputs.
October 21, 2025 at 4:39 PM
Reposted by Adrian Hill @ NeurIPS San Diego
typst.app
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
October 21, 2025 at 7:48 AM
Reposted by Adrian Hill @ NeurIPS San Diego
mm-jj-nn.bsky.social
Didn’t we use to measure this in FLOPS? www.ft.com/content/bdaf...
“When completed, the deals would bring OpenAI’s total access to computing capacity to more than 26GW”
October 14, 2025 at 1:24 PM
adrianhill.de
Kind of hilarious that functional programming's biggest hit is a package manager
October 9, 2025 at 6:09 PM
adrianhill.de
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...
September 30, 2025 at 12:05 PM
adrianhill.de
Based on my own mediocre experiences with LLM-assisted coding, I can't help but wonder whether this explains the recent engineering issues Anthrophic was facing.
gergely.pragmaticengineer.com Gergely Orosz @gergely.pragmaticengineer.com · Sep 19
Talked with the Claude Code team on how they build Claude Code. It feels I get a peek into the future, and I get why Dario said 6 months ago that 90% of code will be written by AI.

This team works SO differently than any eng team I saw. Will share in-depth soon. One example:
September 22, 2025 at 1:06 PM
adrianhill.de
This also shows that @typst.app is already a viable alternative to LaTeX for top conferences in ML!
adrianhill.de Adrian Hill @ NeurIPS San Diego @adrianhill.de · Sep 19
Our paper on XAI + Automatic Differentiation got accepted at #NeurIPS2025. Can't wait to share the camera-ready soon! 🥳
September 19, 2025 at 11:54 AM
adrianhill.de
Our paper on XAI + Automatic Differentiation got accepted at #NeurIPS2025. Can't wait to share the camera-ready soon! 🥳
September 19, 2025 at 11:48 AM
adrianhill.de
Doing XAI research in #JuliaLang
A depressed and jaded Sisyphus pushing a boulder with the Python logo up a mild incline. A happy and fulfilled Sisyphus pushing a boulder with the Julia logo up a steep incline.
September 15, 2025 at 8:40 PM
adrianhill.de
This is 100% true, including the H100 being 12.3 km away.
ericbrachmann.bsky.social Eric Brachmann @ericbrachmann.bsky.social · Sep 3
Did you know in Germany, there are signs in every city indicating the way to the closest H100, in case of an upcoming deadline?
September 3, 2025 at 11:35 AM
adrianhill.de
Is anyone cross-posting on both Bsky and Mastodon? Is it worth the effort? If so, are there tools you would recommend?
August 27, 2025 at 11:23 AM
adrianhill.de
Just noticed my "Julia for Machine Learning" course got 2^8 stars on GitHub, yay! 🎉
github.com/adrhill/juli...
GitHub - adrhill/julia-ml-course: Julia Programming for Machine Learning course at TU Berlin
Julia Programming for Machine Learning course at TU Berlin - adrhill/julia-ml-course
github.com
August 25, 2025 at 2:32 PM
Reposted by Adrian Hill @ NeurIPS San Diego
simi.bsky.social
I’m happy to announce BonitoBook, a Jupyter alternative with a focus on plotting, customizability, dashboards and AI integration.

Visit the website to learn more:

bonitobook.org

Or the repository:

github.com/SimonDanisch...
August 7, 2025 at 11:57 AM
adrianhill.de
We implemented and evaluated the ideas from our NeurIPS submission in Julia and reviewer 2 tells us that one of our strengths is that "It builds on PyTorch". 🫠

What a way to tell me you haven't read the paper before scoring it with high "confidence".
July 25, 2025 at 11:43 AM