Lightnews — Scholar-powered news

Will Smith @willsmithvision.bsky.social · May 11

Or maybe in the style of Dr Seuss. Or Shakespeare.

If so, did it work? Asking for a friend...

Will Smith @willsmithvision.bsky.social · May 11

Has anyone ever tried a very non-standard tone for a rebuttal? I'm thinking something like "Hey reviewers! Sit back, relax and let me convince you that you actually want to accept this paper..." or "You wouldn't let a little thing like that stop you accepting the paper would you? WOULD YOU?!!!"

2 2

Will Smith @willsmithvision.bsky.social · Apr 1

The date is just an unfortunate coincidence. This is a genuine SIGBOVIK submission and the full working source code is in our arXiv repository.

2

Will Smith @willsmithvision.bsky.social · Apr 1

Web: neuralatex.com
Paper: arxiv.org/abs/2503.24187
Source: arxiv.org/abs/2503.24187 (click "TeX source")

Neuralatex: A machine learning library written in pure LATEX

neuralatex.com

1 3

Will Smith @willsmithvision.bsky.social · Apr 1

This has been a massively entertaining and challenging side project with @jadgardner.bsky.social and @willrowan.bsky.social over the past year and (subject to rigorous peer review) will be appearing at SIGBOVIK 2025.

1 4

Will Smith @willsmithvision.bsky.social · Apr 1

@overleaf.com becomes your cloud compute provider. This should level the playing field within the community as both industry and academia will have to work within the same compute limits.

1 5

Will Smith @willsmithvision.bsky.social · Apr 1

NeuRaLaTeX brings many side benefits. Your paper source code is also your method source code. No more "Code coming soon" on github. If the paper is on arxiv, the paper source link *is* the method source code! No need to remember those silly git commands anymore!

1 3

Will Smith @willsmithvision.bsky.social · Apr 1

In case your arXiv submission is timing out, we've also implemented checkpointing so you can include your trained model weights as a text file with your paper source.

1 3

Will Smith @willsmithvision.bsky.social · Apr 1

In a NeuRaLaTeX paper, when you compile your PDF, a neural network is constructed, trained and evaluated with all results and figures generated dynamically. We've worked hard on efficiency and the NeuRaLaTeX paper only took 48 hours to compile.

1 3

Will Smith @willsmithvision.bsky.social · Apr 1

Our neural network library extends the autograd engine to create neurons, linear layers and MLPs. Constructing an MLP and making a forward pass is as easy as this.

1 2

Will Smith @willsmithvision.bsky.social · Apr 1

Just like Karpathy's micrograd, NeuRaLaTeX implements backpropagation (reverse-mode autodiff) over a dynamically built DAG. However, while micrograd uses 150 lines of Python, NeuRaLaTeX uses around 1,100 line of pure LaTeX, making it about 700% better.

1 7

Will Smith @willsmithvision.bsky.social · Apr 1

Not only that, but LaTeX has elegant and intuitive programming syntax. For example, creating a new Value object only uses the word "expand" four times:
\expanded{
\noexpand\pgfoonew\expandafter\noexpand
\csname #2\endcsname=
new Value(\newdata,{\selfid,\otherid},*,0)
}

1 3

Will Smith @willsmithvision.bsky.social · Apr 1

Wait, what?

Well, LaTeX is itself a Turing-complete programming language. When you "compile" a LaTeX document, really you are executing a program written in LaTeX. This program need not only format your paper contents into a PDF but can also perform useful computation.

1 3

Will Smith @willsmithvision.bsky.social · Apr 1

So, we wrote a neural net library entirely in LaTeX...

3 15 81

Will Smith @willsmithvision.bsky.social · Mar 7

On a similar note: if you have two figures one above the other at the top of one column, move one figure to the top of the other column and you gain the white space between them.

3

Reposted by Will Smith

Jon Barron @jonbarron.bsky.social · Feb 18

I just pushed a new paper to arXiv. I realized that a lot of my previous work on robust losses and nerf-y things was dancing around something simpler: a slight tweak to the classic Box-Cox power transform that makes it much more useful and stable. It's this f(x, λ) here:

2 23 110

Will Smith @willsmithvision.bsky.social · Jan 17

I must confess I just immediately copy/pasted the turkey eggs question into ChatGPT to get the answer myself. Great question!

2

Will Smith @willsmithvision.bsky.social · Jan 14

#CVPR2025 Area Chair update: depending on which time zone the review deadline is specified in, we are past or close to the review deadline. Of the 60 reviews needed for my batch, I currently have 52 and they have been coming in quite fast this morning. In general, review standard looks good.

3

Reposted by Will Smith

Dmytro Mishkin @ducha-aiki.bsky.social · Jan 2

Image matching and ChatGPT - new post in the wide baseline stereo blog.

tl;dr: it is good, even feels like human, but not perfect.
ducha-aiki.github.io/wide-baselin...

ChatGPT and Image Matching – Wide baseline stereo meets deep learning

Are we done yet?

ducha-aiki.github.io

2 8 34

Reposted by Will Smith

Gabriele Berton @berton-gabri.bsky.social · Dec 19

This simple pytorch trick will cut in half your GPU memory use / double your batch size (for real). Instead of adding losses and then computing backward, it's better to compute the backward on each loss (which frees the computational graph). Results will be exactly identical

4 7 54

Will Smith @willsmithvision.bsky.social · Dec 18

Enjoy! on.soundcloud.com/2ALY7LnJrmiR... 5/5

Turning scholarship into an “engaging” podcast using AI: interdisciplinary perspectives

AI generated podcast to accompany the blog post

on.soundcloud.com

Will Smith @willsmithvision.bsky.social · Dec 18

Of course, we then put our blog post back through the podcast generator! So now its AI podcast hosts talking about our blog post about themselves talking about our research - how meta is that?! They have some minor existential crises as they discuss that they are themselves LLMs. 4/5

1

Will Smith @willsmithvision.bsky.social · Dec 18

On another level, we noticed that it made fundamental mistakes. Often these were wrapped up within clever metaphors that gave a falsely confident impression that it deeply understood the material. We were left wondering what effect a deluge of these accessible but incorrect podcasts might have. 3/5

1 1 2

Will Smith @willsmithvision.bsky.social · Dec 18

When NotebookLM launched the podcast feature, we both put our own papers through it and chatted about what we thought of it. On one level, we were blown away by the convincing podcast style and the way it seemed to distill complex research into an accessible form. 2/5

1

Will Smith @willsmithvision.bsky.social · Dec 18

Me and my friend-since-before-school @ekd.bsky.social (a law academic) have written a blog post about the NotebookLM podcast generator in the style of, well, a corny podcast dialogue: slsablog.co.uk/blog/blog-po... 1/5

Turning scholarship into an "engaging" podcast using AI: interdisciplinary perspectives

by Dr Edward Kirton-Darling, Senior Lecturer at the University of Bristol Law School, and Professor Will Smith, Department for Computer Science, University of York, Ed & Will in 1987 (or is it?) ...

slsablog.co.uk

1 1