iiinova — where your digital self keeps evolving

Reposted by Matheus Gadelha

Gautam Kamath @gautamkamath.com · 18/08/2026

Obviously this doesn't scale, but I chose to send this junior researcher a (hopefully polite) email with some of my thoughts (written hastily in 30 minutes, not polished). More practicing mathematicians & researchers should advocate for the culture they want, so here's my bit.

1234

Reposted by Matheus Gadelha

Christian Wolf @chriswolfvision.bsky.social · 04/08/2026

Rebuttals and discussions need to be reduced an extreme minimal length. CVPR style, 1 single PDF page. No discussion. Else, human ACs and reviewers will have a disadvantage compared to the world of agents out there now.

2233

Reposted by Matheus Gadelha

Shriram Krishnamurthi @shriram.bsky.social · 28/07/2026

0/ At the AIMCS (AI for Math and CS) workshop at FLoC 2026, @swarat.bsky.social ran a really fun panel on "How should the Formal Methods community respond to AI progress?" He put a lot of thought into very good questions, so here are my answers to them: ↵

1134

Reposted by Matheus Gadelha

Yining Karl Li @yiningkarlli.bsky.social · 14/07/2026

Woah, almost all of EGSR 2026 was recorded, and they posted it all to Youtube. Wow! Big props to the conference organizers for doing this! www.youtube.com/@egsr2026/pl...

youtube.com

EGSR 2026

The 37th Eurographics Symposium on Rendering (EGSR 2026), Bordeaux (France).

0163

Reposted by Matheus Gadelha

ICML Conference @icmlconf.bsky.social · 10/07/2026

We appreciate the love ❤️ But limited engagement and few followers on Bsky makes some (not us!) question whether it's worth it Be sure to follow (and share with your ML friends!) if you want to see more updates from ICML!

610924

Reposted by Matheus Gadelha

Gabriel Peyré @gabrielpeyre.bsky.social · 02/07/2026

Slides for an introductory talk on IA for maths. speakerdeck.com/gpeyre/ia-fo...

speakerdeck.com

IA for theory

Slide for an introduction talk on IA for maths.

1329

Matheus Gadelha @gadelha.bsky.social · 24/03/2026

Text-to-image models are remarkable at generation, but they end up deciding on their own what goes where. If you need specific subjects in a specific arrangement, you are left writing prompts and sampling until something usable appears. SIGMA-Gen, our new ICLR 2026 paper, tries to change that.

150

Matheus Gadelha @gadelha.bsky.social · 04/03/2026

PSA (this sounds like something pretty important that I should know but could have lived the rest of my life in shame without ever learning it)

010

Reposted by Matheus Gadelha

Igor Gilitschenski @igilitschenski.bsky.social · 13/02/2026

🚀 Excited to share REPPO, a new on-policy RL agent! TL;DR: Replace PPO with REPPO for fewer hyperparameter headaches and more robust training. REPPO, led by @cvoelcker.bsky.social, will be presented at ICLR 2026. How does it work? 🧵👇

12510

Matheus Gadelha @gadelha.bsky.social · 09/01/2026

Great resource! This is specially important for people starting their research careers. Getting to know different research communities is really important! Technical insight is crucial, but science is ultimately a social endeavor -- understanding and communicating to your peers is key.

131

Reposted by Matheus Gadelha

Aaron Hertzmann @aaronhertzmann.com · 26/11/2025

As we in the US gather with our families this weekend, it's a good time to consider the ways that technology brings us together—but also keeps us apart. In this blog post, I tell a story about how technology may have tended to increase social isolation. aaronhertzmann.com/2025/10/26/i...

aaronhertzmann.com

Technology and Social Isolation: From Cars to “AI”

In this blog post, I tell a story of how some technologies from the past century or so have, overall, led to increased social isolation in the United States, as we replaced in-person social interactio...

074

Reposted by Matheus Gadelha

Alexander Doria @dorialexander.bsky.social · 10/11/2025

Breaking: we release a fully synthetic generalist dataset for pretraining, SYNTH and two new SOTA reasoning models exclusively trained on it. Despite having seen only 200 billion tokens, Baguettotron is currently best-in-class in its size range. pleias.fr/blog/blogsyn...

318833

Matheus Gadelha @gadelha.bsky.social · 23/10/2025

Session this afternoon (in 30 minutes)!! Poster 153 — see you there!

020

Reposted by Matheus Gadelha

David Picard @davidpicard.eurosky.social · 27/06/2025

I wrote a notebook for a lecture/exercice on image generation with flow matching. The idea is to use FM to render images composed of simple shapes using their attributes (type, size, color, etc). Not super useful but fun and easy to train! colab.research.google.com/drive/16GJyb... Comments welcome!

2418

Matheus Gadelha @gadelha.bsky.social · 11/06/2025

For folks attending CVPR: is there a website where I can see the list of workshops, their location AND time? Day and time are empty when I access cvpr.thecvf.com/Conferences/...

cvpr.thecvf.com

CVPR 2025 Workshop List

010

Matheus Gadelha @gadelha.bsky.social · 09/06/2025

I will be in Nashville until Saturday for CVPR'25 \o/ DM if you want to meet!

060

Reposted by Matheus Gadelha

Élie Michel @elie-michel.bsky.social · 19/05/2025

🏅Honored to have been awarded at #Eurographics25 for our paper on #LipschitzPruning to speed-up SDF rendering! 👉 The paper's page: wbrbr.org/publications... Congrats to @wbrbr.bsky.social, M. Sanchez, @axelparis.bsky.social, T. Lambert, @tamyboubekeur.bsky.social, M. Paulin and T. Thonat!

0254

Matheus Gadelha @gadelha.bsky.social · 14/05/2025

NeurIPS and SIGGRAPH Asia deadline are coming. Make your life easier: read this thread.

172

Matheus Gadelha @gadelha.bsky.social · 28/04/2025

Let's gooo!!! \o/ Probably my first time visiting Brazil for professional reasons :-)

040

Reposted by Matheus Gadelha

#CVPR2026 @cvprconference.bsky.social · 27/02/2025

By popular demand, we are extending #CVPR2025 coverage to Bluesky. Stay tuned!

512417

Reposted by Matheus Gadelha

Angjoo Kanazawa @akanazawa.bsky.social · 24/02/2025

Exciting news! MegaSAM code is out🔥 & the updated Shape of Motion results with MegaSAM are really impressive! A year ago I didn't think we could make any progress on these videos: shape-of-motion.github.io/results.html Huge congrats to everyone involved and the community 🎉

37417

Matheus Gadelha @gadelha.bsky.social · 23/02/2025

I understand the sentiment, but it is important for people to know that is currently does not reflect reviewer guidelines at CVPR: cvpr.thecvf.com/Conferences/... “(…) you should include specific feedback on ways the authors can improve their papers.”

cvpr.thecvf.com

2025 Reviewer Guidelines

250

Reposted by Matheus Gadelha

Qianqian Wang @qianqianwang.bsky.social · 18/02/2025

Late to post, but excited to introduce CUT3R! An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one! Project Page: cut3r.github.io Code and Model: github.com/CUT3R/CUT3R

2346

Reposted by Matheus Gadelha

Harry Thasarathan @hthasarathan.bsky.social · 07/02/2025

🌌🛰️🔭Wanna know which features are universal vs unique in your models and how to find them? Excited to share our preprint: "Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment"! arxiv.org/abs/2502.03714 (1/9)

15617

Reposted by Matheus Gadelha

Aaron Hertzmann @aaronhertzmann.com · 06/02/2025

New paper about pictures: I identify trends in geometric perspective in my own drawings and photos, and compare them to how the original scenes looked. I discuss what these trends might say about art history and vision science. Published in _Art & Perception_. #visionscience psyarxiv.com/pq8nb

psyarxiv.com

OSF

3196

Reposted by Matheus Gadelha

Andrea Tagliasacchi @taiyasaki.bsky.social · 05/02/2025

"𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing" A mesh-based 3D represention for training radiance fields from collections of images. radfoam.github.io arxiv.org/abs/2502.01157 Project co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ co-advisor Kwang Moo Yi

25412

Matheus Gadelha @gadelha.bsky.social · 03/02/2025

#CVPR2025 Is there any way in OpenReview to "mention" a reviewer in a discussion? I think reviewers get the e-mail with whatever message gets posted in the discussion that is sent to them, but they have no idea if Reviewer HjKl is them or someone else...

110

Matheus Gadelha @gadelha.bsky.social · 23/01/2025

I will keep repeating this until I convince everyone I work with or I will die trying.

081

Matheus Gadelha @gadelha.bsky.social · 15/01/2025

It would *really* help if OpenReview showed how many reviews a paper already had on the reviewer assignment page

010

Matheus Gadelha @gadelha.bsky.social · 14/01/2025

This is a great speaker lineup and I will definitely try to attend. I can't help but think though: if everyone is trying to stand out you will stand out by not trying to :-) (I am obviously kidding, the workshop is about more than that, visit the webpage to learn more)

150

Matheus Gadelha @gadelha.bsky.social · 07/01/2025

If you are an undergrad/MS student interested in graphics, geometry, applied math, etc, I strongly recommend SGI. Apply! vvvvv

1103

Reposted by Matheus Gadelha

Dmytro Mishkin @ducha-aiki.bsky.social · 06/01/2025

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models Zehan Wang, Ziang Zhang, Tianyu P tl;dr: train ViT on Objaverse(800K->55K obj after filtering)to predict canonical ori->PROFIT arxiv.org/abs/2412.18605

281

Reposted by Matheus Gadelha

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 02/01/2025

Physics has a set of useful numbers that you can use for quick order-of-magnitude estimation: densities of some common materials, energies in bonds, interatomic spacing, etc. What are the equivalently useful numbers, worth memorizing for estimating economic / political things? Some of mine: 1/2

3151

Reposted by Matheus Gadelha

Antoine Guédon @antoine-guedon.bsky.social · 11/12/2024

⚠️Reconstructing sharp 3D meshes from a few unposed images is a hard and ambiguous problem. ☑️With MAtCha, we leverage a pretrained depth model to recover sharp meshes from sparse views including both foreground and background, within mins!🧵 🌐Webpage: anttwo.github.io/matcha/

43811

Reposted by Matheus Gadelha

Giorgos Tolias @gtolias.bsky.social · 06/12/2024

Introducing a new composed (image + text query) image retrieval method that enables domain conversion—style, context, or background—of objects.

1124

Reposted by Matheus Gadelha

F. Güney @fguney.bsky.social · 05/12/2024

I could easily spend an afternoon looking at the results of this paper: motionmodes.github.io or this paper: rollingdepth.github.io or this paper: romosfm.github.io vision is cool 😎

motionmodes.github.io

Motion Modes: What Could Happen Next?

Motion Modes is the first training-free method to generate multiple plausible yet distinct motions for a given object, disentangled from the motion of other objects, camera and other scene changes, fr...

1208

Matheus Gadelha @gadelha.bsky.social · 04/12/2024

Fast text-guided 3D editing! We trained a multi-view inpainting model to consistently “fill” masked regions in 3D. Full process takes as much time as doing image inpainting + reconstruction (experiments in the paper). Internship project led by Amir Barda! amirbarda.github.io/Instant3dit....

amirbarda.github.io

Instant3dit

Multiview Inpainting for Fast Editing of 3D Objects

060

Matheus Gadelha @gadelha.bsky.social · 03/12/2024

This example should convey what we are doing pretty well: just starting from different noises will not lead to diverse *object motions*. More results in the website: motionmodes.github.io

020

Matheus Gadelha @gadelha.bsky.social · 03/12/2024

Generating diverse object motions from a single image; turns out no training is needed — just applying additional regularization during the diffusion process leads to surprisingly good results! Work led by Karran Pandey (karranpandey.github.io) during his summer internship at Adobe!

010

Matheus Gadelha @gadelha.bsky.social · 03/12/2024

This will be presented Tue afternoon JST! Make sure to attend and chat with Yun-Chun if you are at the conference!

042

Reposted by Matheus Gadelha

Lily Goli @lilygoli.bsky.social · 02/12/2024

Hello everyone!! 👋 Excited to be here and share our latest work to get started! RoMo: Robust Motion Segmentation Improves Structure from Motion romosfm.github.io Boost the performance of your SfM pipeline on dynamic scenes! 🚀 RoMo masks dynamic objects in a video, in a zero-shot manner.

1277

Reposted by Matheus Gadelha

Jeremy Howard @howard.fm · 01/12/2024

Free speech on twitter:

51095

Reposted by Matheus Gadelha

Aleksander Hołyński @holynski.bsky.social · 28/11/2024

Check out CAT4D: our new paper that turns (text, sparse images, videos) => (dynamic 3D scenes)! I can't get over how cool the interactive demo is. Try it out for yourself on the project page: cat-4d.github.io

16314

Reposted by Matheus Gadelha

Zhenjun Zhao @ericzzj.bsky.social · 27/11/2024

G2SDF: Surface Reconstruction from Explicit Gaussians with Implicit SDFs Kunyi Li, Michael Niemeyer, Zeyu Chen, Nassir Navab, Federico Tombari tl;dr: SDF-to-Opacity function->SDF->Gaussian opacities; coordinate normalization->unbounded 3D coordinates->0-1 range arxiv.org/abs/2411.16898

061

Reposted by Matheus Gadelha

Simon Niklaus @sniklaus.com · 26/11/2024

A nifty application of depth estimation, creating a mockup of a digital design on real-world objects: sniklaus.com/mockup

092

Reposted by Matheus Gadelha

Élie Michel @elie-michel.bsky.social · 26/11/2024

Sharing a starter setup for using @shader-slang.bsky.social with #WebGPU in C++ with #CMake, either for native or web targets. 🔹 Uses the #reflection API to auto-generate boilerplate code! ✨ 👉 github.com/eliemichel/S... Very happy to take feedback about what's good and bad in this demo! More⤵️ 1/8

Screenshot of Slang x WebGPU README on GitHub (where the link in the post points)

23915

Reposted by Matheus Gadelha

International Conference on 3D Vision @3dvconf.bsky.social · 26/11/2024

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!

134514