Very excited to be in Rio for #ICLR2026 presenting my poster for CroCoDiLight! If anyone is also here, please pop by and say hi! I'd love to chat. I'll be at poster session 2 in pavilion 4 this afternoon

Excited to announce our latest (submitted to) SIGBOVIK 2026 @harryqbovik.bsky.social paper: "SchmidhubAI: Accurate Historical Paper Attribution". We built an AI system that, given any modern AI paper, automatically determines which of its ideas were already published by Jürgen Schmidhuber.

wait no this is actually incredible youraislopbores.me

innes mck@innes.bsky.social · 5mo ago

wow it works

I am delighted (that pun will make sense in a second) that @alistairfoggin.bsky.social's first paper, CroCoDiLight, has been accepted to ICLR. The idea came from a group discussion on the CroCo paper from @naverlabseurope.bsky.social and realising it might implicitly already understand relighting.

Alistair Foggin@alistairfoggin.bsky.social · 5mo ago

Very excited to announce my first paper, CroCoDiLight! Co-authored with @willsmithvision.bsky.social and accepted at #ICLR2026. Image relighting, shadow removal, and albedo estimation, all in our single base model with swappable task components. See you in Rio @iclr-conf.bsky.social! [1/7]

The LLM obsession with em-dashes has created a weird sort of paradox. I see so much AI generated content that I now see how I should have been using em-dashes all along. But if I start using them, everyone will assume what I've written is AI generated.

Excited to share our Paper - VENI: Variational Encoder for Natural Illumination 🌐 🔗 Project page: paul-pw.github.io/veni/ 📄 Paper: arxiv.org/abs/2601.14079 👩‍💻 Code: github.com/paul-pw/veni 🧵 (1/5)

My students @fhudson.bsky.social and @jadgardner.bsky.social are presenting TAPVid-360 at NeurIPS this week. We introduce an interesting new problem, a benchmark dataset and a baseline adaptation of an existing TAP model for our task. More importantly, they've also created a genre-defining poster...

Finlay Hudson@fhudson.bsky.social · 8mo ago

TAPVid-360 will be at NeurIPS25 this week in sunny San Diego!! This work involves models having to understand beyond a camera’s field of view without the need for expensive 3D data. 👇 1/5

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?!!!"

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

James Gardner@jadgardner.bsky.social · last yr.

Are you tired of context-switching between coding models in @pytorch.org and paper writing on @overleaf.com? Well, I’ve got the fix for you, Neuralatex! An ML library written in pure Latex! neuralatex.com To appear in Sigbovik (subject to rigorous review process)

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:

#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.

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...

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

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

Entropy is one of those formulas that many of us learn, swallow whole, and even use regularly without really understanding. (E.g., where does that “log” come from? Are there other possible formulas?) Yet there's an intuitive & almost inevitable way to arrive at this expression.

"Sora is a data-driven physics engine." x.com/chrisoffner3...

Multistable Shape from Shading Emerges from Patch Diffusion #NeurIPS2024 Spotlight X. Nicole Han, T. Zickler and K. Nishino (Harvard+Kyoto) Diffusion-based SFS lets you sample multistable shape perception! Nicole at poster on Th 12/12 11am East A-C 1308 vision.ist.i.kyoto-u.ac.jp/research/mss...

To kick off using Bluesky: our new dataset called Oxford Spires. Synchronised, multi-color cameras and lidar in multiple Oxford colleges. Ground-Truth highly accurate 3D maps from tripod scanners. The ideal basis for NeRF/3DGS SLAM research. dynamic.robots.ox.ac.uk/datasets/oxf...

Introducing MegaSaM! Accurate, fast, & robust structure + camera estimation from casual monocular videos of dynamic scenes! MegaSaM outputs camera parameters and consistent video depth, scaling to long videos with unconstrained camera paths and complex scene dynamics!

OK If we are moving to Bluesky I am rescuing my favourite ever twitter thread (Jan 2019). The renamed: Bluesky-sized history of neuroscience (biased by my interests)

Really cool new work out of Deep Mind for video game world generation using latent diffusion! Soon you'll be able to speed run a game just by tricking a model to morph you from one location to another. deepmind.google/discover/blo...

Genie 2: A large-scale foundation world model

Generating unlimited diverse training environments for future general agents

deepmind.google

How to drive your research forward? “I tested the idea we discussed last time. Here are some results. It does not work. (… awkward silence)” Such conversations happen so many times when meetings with students. How do we move forward? You need …

For my first post on Bluesky, this recent talk I did at the recent BMVA one day meeting on World Models is a good summary of my work on Computer Vision, Robotics and SLAM, and my thoughts on a bigger picture of #SpatialAI. youtu.be/NLnPG95vNhQ?...

1 Andrew Davison, Imperial College London - BMVA Symposium: Robotics Foundation & World Models

YouTube video by BMVA: British Machine Vision Association

youtu.be

I am a first time Area Chair for #CVPR2025 so, in the interests of transparency, I'll post some updates here on the various stages of the process. There are 708 (!) ACs (not that long ago, CVPR could have coped with 708 *reviewers*!) We've been allocated 18.27 papers on average (I have 20).

Hello Bluesky! 🔵 We start our account by having our third guess for Ask Me Anything session #3DV2025AMA! Noah Snavely @snavely.bsky.social from Cornell & Google DeepMind! 🌟 🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below! Keep it engaging but respectful!

Introducing Generative Omnimatte: A method for decomposing a video into complete layers, including objects and their associated effects (e.g., shadows, reflections). It enables a wide range of cool applications, such as video stylization, compositions, moment retiming, and object removal.

A real-time (or very fast) open-source txt2video model dropped: LTXV. HF: huggingface.co/Lightricks/L... Gradio: huggingface.co/spaces/Light... Github: github.com/Lightricks/L... Look at that prompt example though. Need to be a proper writer to get that quality.

I used 📍🔗 emojis to maximize Twitter/Bluesky parity in my profile. This is definitely pointless, but it's fun.

NeurIPS Conference is now Live on Bluesky! -NeurIPS2024 Communication Chairs

We've released our paper "Generating 3D-Consistent Videos from Unposed Internet Photos"! Video models like Luma generate pretty videos, but sometimes struggle with 3D consistency. We can do better by scaling them with 3D-aware objectives. 1/N page: genechou.com/kfcw