iiinova — where your digital self keeps evolving

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 12/11/2025

🚀 New paper: ConeGS Error-Guided Densification Using Pixel Cones. We improve 3D Gaussian Splatting by placing Gaussians where they matter most: ConeGS adds primitives along pixel-view cones guided by image error, boosting quality with fewer Gaussians. baranowskibrt.github.io/conegs/

0143

Reposted by Stefano Esposito

Zhenjun Zhao @ericzzj.bsky.social · 11/11/2025

ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives Bartłomiej Baranowski, @s-esposito.bsky.social, @pgschossmann.bsky.social, @apchen.bsky.social, @andreasgeiger.bsky.social arxiv.org/abs/2511.06810

151

Reposted by Stefano Esposito

Aaron Hertzmann @aaronhertzmann.com · 29/09/2025

Here's a recording of my talk on how perspective works! If you're interested in learning about how picture perspective works in human vision, this is the video to watch. #visionscience www.youtube.com/watch?v=eamc...

youtube.com

Picture Perspective and Our Eyes

YouTube video by Aaron Hertzmann

2196

Reposted by Stefano Esposito

Vision and Graphics Trends @si-cv-graphics.bsky.social · 04/09/2025

𝟯𝗗-𝗟𝗔𝗧𝗧𝗘: 𝗟𝗮𝘁𝗲𝗻𝘁 𝗦𝗽𝗮𝗰𝗲 𝟯𝗗 𝗘𝗱𝗶𝘁𝗶𝗻𝗴 𝗳𝗿𝗼𝗺 𝗧𝗲𝘅𝘁𝘂𝗮𝗹 𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻𝘀 Maria Parelli, Michael Oechsle, Michael Niemeyer ... Andreas Geiger arxiv.org/abs/2509.00269 Trending on www.scholar-inbox.com

033

Reposted by Stefano Esposito

haoyuhe.bsky.social @haoyuhe.bsky.social · 20/08/2025

🚀 Introducing our new paper, MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models. 📄 Paper: www.scholar-inbox.com/papers/He202... arxiv.org/pdf/2508.13148 💻 Code: github.com/autonomousvi... 🌐 Project Page: cli212.github.io/MDPO/

1128

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 21/07/2025

Today, we moved into our new building on the CyberValley campus. Everyone is super excited. PhD students went right back to work. But wait, is there something missing? ;)

1351

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 18/07/2025

Today we had our AVG Deep Cave Expedition Day! Exploring the challenges of the (unlit, narrow, crawling-only) Hofener Höhle near Grabenstetten ..

0191

Reposted by Stefano Esposito

Zhenjun Zhao @ericzzj.bsky.social · 17/07/2025

SpatialTrackerV2: 3D Point Tracking Made Easy Yuxi Xiao, @jianyuanwang.bsky.social, Nan Xue, @nikkar.bsky.social, Yuri Makarov, Bingyi Kang, Xing Zhu, Hujun Bao, Yujun Shen, Xiaowei Zhou tl;dr: DAv2+VGGT->depths & poses->iterative cross-attention-based optimizer arxiv.org/abs/2507.12462

022

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 15/07/2025

In case you find it as relaxing as we do: Here is a 2h+ video of our autonomous RL driving agent CaRL in action! @danieldauner.bsky.social @bernhard-jaeger.bsky.social @kashyap7x.bsky.social youtube.com/watch?v=_god...

youtube.com

CaRL: Learning Scalable Planning Policies with Simple Rewards

YouTube video by Daniel Dauner

0215

Reposted by Stefano Esposito

Claire Vernade @claireve.bsky.social · 15/07/2025

At #ICML, you can just use scholar inbox to help you find your way through the poster sessions. It just sorts the papers according to your preferences and it really works. www.scholar-inbox.com/conference/i... ICML 2025 Planner

3505

Reposted by Stefano Esposito

Onno Eberhard @onnoeberhard.com · 16/07/2025

I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵

36012

Reposted by Stefano Esposito

Bernhard Jaeger @bernhard-jaeger.bsky.social · 15/07/2025

We have released the code for our work, CaRL: Learning Scalable Planning Policies with Simple Rewards. The repository contains the first public code base for training RL agents with the CARLA leaderboard 2.0 and nuPlan. github.com/autonomousvi...

github.com

GitHub - autonomousvision/CaRL: [ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards

[ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards - autonomousvision/CaRL

0207

Reposted by Stefano Esposito

Mehdi S. M. Sajjadi @msajjadi.com · 10/07/2025

Scaling 4D Representations Self-supervised learning from video does scale! In our latest work, we scaled masked auto-encoding models to 22B params, boosting performance on pose estimation, tracking & more. Paper: arxiv.org/abs/2412.15212 Code & models: github.com/google-deepmind/representations4d

0208

Reposted by Stefano Esposito

Vision and Graphics Trends @si-cv-graphics.bsky.social · 04/07/2025

𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆-𝗮𝘄𝗮𝗿𝗲 𝟰𝗗 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗥𝗼𝗯𝗼𝘁 𝗠𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 Zeyi Liu, Shuang Li, Eric Cousineau ... Shuran Song arxiv.org/abs/2507.01099 Trending on www.scholar-inbox.com

054

Reposted by Stefano Esposito

Zhenjun Zhao @ericzzj.bsky.social · 04/07/2025

MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details Ruicheng Wang, Sicheng Xu, Yue Dong, Yu Deng, Jianfeng Xiang, Zelong Lv, Guangzhong Sun, Xin Tong, Jiaolong Yang arxiv.org/abs/2507.02546

154

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 03/07/2025

I am very proud of my group! These are the nationalities of my current and past team members. Diversity is key. 🇩🇪 🇬🇷 🇮🇹 🇮🇳 🇷🇺 🇺🇦 🇨🇳 🇷🇸 🇯🇵 🇧🇪 🇺🇸 🇰🇷 🇹🇷

1491

Reposted by Stefano Esposito

#CVPR2026 @cvprconference.bsky.social · 15/06/2025

That’s a wrap on #CVPR2025 in Nashville! From online convos to in-person vibes, one thing’s clear: this community is STRONG 💪 Thanks for following along! Until next time. @deblinaml.bsky.social, @jbhaurum.bsky.social, @csprofkgd.bsky.social signing off.

0123

Reposted by Stefano Esposito

Melanie Mitchell @melaniemitchell.bsky.social · 15/06/2025

LLM product placement and search optimization is here and it's as dystopian as you expected.

33810

Stefano Esposito @s-esposito.bsky.social · 15/06/2025

Hey #CVPR2025! Curious about this work? I'll be presenting it this morning! Poster 31, from 10:30 to 12:30 🤠 @cvprconference.bsky.social

081

Reposted by Stefano Esposito

Angela Dai @adai.bsky.social · 08/06/2025

Check out the ScanNet++ workshop @CVPR on June 12 in 211 from 8:50am! Exciting keynotes on state-of-the-art NVS & 3D understanding from Andrea Vedaldi, Cordelia Schmid, Gordon Wetzstein, Katja Schwarz, Qianqian Wang, and leading methods on the benchmark! kaldir.vc.in.tum.de/scannetpp/cv...

0136

Reposted by Stefano Esposito

Elliott / Shangzhe Wu @elliottwu.bsky.social · 09/06/2025

Join us for the 4D Vision Workshop #CVPR on June 11 starting at 9:20am! We'll have an incredible lineup of speakers discussing the frontier of 3D computer vision techniques for dynamic world modeling across spatial AI, robotics, astrophysics, and more. 4dvisionworkshop.github.io

092

Reposted by Stefano Esposito

Ilya Chugunov @ilyac.info · 09/06/2025

This Wednesday (1-6PM, Room 106A) at CVPR @cvprconference.bsky.social we have a great lineup of keynote speakers, posters, and spotlights on neural fields and beyond: neural-bcc.github.io Have a question you want answered by a panel of experts in the field? Send it to us via: tinyurl.com/bdddf36f

0112

Reposted by Stefano Esposito

Haofei Xu @haofeixu.bsky.social · 05/06/2025

Excited to present our #CVPR2025 paper DepthSplat next week! DepthSplat is a feed-forward model that achieves high-quality Gaussian reconstruction and view synthesis in just 0.6 seconds. Looking forward to great conversations at the conference!

3267

Reposted by Stefano Esposito

Kashyap Chitta @kashyap7x.bsky.social · 05/06/2025

🚗 Pseudo-simulation combines the efficiency of open-loop and robustness of closed-loop evaluation. It uses real data + 3D Gaussian Splatting synthetic views to assess error recovery, achieving strong correlation with closed-loop simulations while requiring 6x less compute. arxiv.org/abs/2506.04218

02210

Reposted by Stefano Esposito

Matthias Niessner @niessner.bsky.social · 27/05/2025

🚀🚀🚀Announcing our $13M funding round to build the next generation of AI: 𝐒𝐩𝐚𝐭𝐢𝐚𝐥 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 that can generate entire 3D environments anchored in space & time. 🚀🚀🚀 Interested? Join our world-class team: 🌍 spaitial.ai youtu.be/FiGX82RUz8U

youtu.be

SpAItial AI: Building Spatial Foundation Models

YouTube video by SpAItial AI

5539

Stefano Esposito @s-esposito.bsky.social · 16/05/2025

"ILM "artists" are now being paid to make shimpanzini bananini and bombardiro crocodilo"

010

Reposted by Stefano Esposito

Felix Wimbauer @fwimbauer.bsky.social · 13/05/2025

Can you train a model for pose estimation directly on casual videos without supervision? Turns out you can! In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors! ⬇️

12410

Reposted by Stefano Esposito

hardmaru @hardmaru.bsky.social · 12/05/2025

New Paper: Continuous Thought Machines pub.sakana.ai/ctm/ Neurons in brains use timing and synchronization in the way that they compute, but this is largely ignored in modern neural nets. We believe neural timing is key for the flexibility and adaptability of biological intelligence. Thread ↓

512929

Reposted by Stefano Esposito

Katrin Renz @katrinrenz.bsky.social · 08/05/2025

📣 Excited to share our #CVPR2025 Spotlight paper and my internship project @wayve: SimLingo. A Vision-Language-Action (VLA) model that achieves state-of-the-art driving performance with language capabilities. Code: github.com/RenzKa/simli... Paper: arxiv.org/abs/2503.09594

1259

Stefano Esposito @s-esposito.bsky.social · 05/05/2025

📢 New paper CVPR 25! Can meshes capture fuzzy geometry? Volumetric Surfaces uses adaptive textured shells to model hair, fur without the splatting / volume overhead. It’s fast, looks great, and runs in real time even on budget phones. 🔗 autonomousvision.github.io/volsurfs/ 📄 arxiv.org/pdf/2409.02482

13221

Reposted by Stefano Esposito

European Commission @ec.europa.eu · 05/05/2025

"Science is an investment. We will put forward a new 500 million package for 2025-2027 to support the best and the brightest researchers and scientists from Europe and around the world." — President @vonderleyen.ec.europa.eu at the ‘Choose Europe for Science' event at La Sorbonne 🇫🇷

35963301

Reposted by Stefano Esposito

Bernhard Jaeger @bernhard-jaeger.bsky.social · 28/04/2025

Introducing CaRL: Learning Scalable Planning Policies with Simple Rewards We show how simple rewards enable scaling up PPO for planning. CaRL outperforms all prior learning-based approaches on nuPlan Val14 and CARLA longest6 v2, using less inference compute. arxiv.org/abs/2504.17838

02414

Reposted by Stefano Esposito

Haiwen Huang @haiwen-huang.bsky.social · 26/04/2025

Sharing another video showing how LoftUp significantly improves DINOv2 features! Works like a charm! Try it out: Code: github.com/andrehuang/l... Paper: arxiv.org/abs/2504.14032

092

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 23/04/2025

New CVPR paper by @s-esposito.bsky.social in collaboration with Peter Kontschieder's team at Meta.

021

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 23/04/2025

Can we represent fuzzy geometry with meshes? "Volumetric Surfaces" uses layered meshes to represent the look of hair, fur & more without the splatting/volume overhead. Fast, pretty, and runs in real-time on your laptop! 🔗 autonomousvision.github.io/volsurfs/ 📄 arxiv.org/pdf/2409.02482

1103

Reposted by Stefano Esposito

Jon Barron @jonbarron.bsky.social · 08/04/2025

A thread of thoughts on radiance fields, from my keynote at 3DV: Radiance fields have had 3 distinct generations. First was NeRF: just posenc and a tiny MLP. This was slow to train but worked really well, and it was unusually compressed --- The NeRF was smaller than the images.

29321

Reposted by Stefano Esposito

Andrew Davison @ajdavison.bsky.social · 25/02/2025

I remember seeing this drone video a few years ago and thinking "we'll never run SLAM on that".... but here it is, complete with dense reconstruction (single camera, unknown calibration, no IMU). MASt3R-SLAM is absurdly robust.

3356

Reposted by Stefano Esposito

👻Notorischer User dieser Plattform🎃 @bildoperationen.bsky.social · 16/02/2025

Apparently, OpenAI is already aligning its LLM to the expectations of the new fascist government – racism, lies, and conspiracy theories will now be sold as «multiple perspectives on controversial subjects» techcrunch.com/2025/02/16/o...

techcrunch.com

OpenAI tries to 'uncensor' ChatGPT | TechCrunch

OpenAI is changing how it trains AI models to explicitly embrace "intellectual freedom … no matter how challenging or controversial a topic may be," the

28595236

Reposted by Stefano Esposito

Chris Offner @chrisoffner3d.bsky.social · 14/02/2025

Trying out monocular depth estimation models on abstract images to see what priors they learned. A human might interpret the top as sky and the bottom as a ground, thus giving the top a constant large (blue) depth and the ground a vertical gradient from low (red) to large depths. The model doesn't.

3362

Reposted by Stefano Esposito

Ben Stiller @benstiller.redhour.com · 31/01/2025

film still #32 Goats #severance photo credit: Trudy Buck

1304421231

Reposted by Stefano Esposito

ian bremmer @ianbremmer.com · 28/01/2025

checking in on deepseek

50482114

Reposted by Stefano Esposito

Karen Hao @karenhao.bsky.social · 27/01/2025

As someone who has reported on AI for 7 years and covered China tech as well, I think the biggest lesson to be drawn from DeepSeek is the huge cracks it illustrates with the current dominant paradigm of AI development. A long thread. 1/

21161252340

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 16/01/2025

This week we had our winter retreat jointly with Daniel Cremer's group in Montafon, Austria. 46 talks, 100 Km of slopes and night sledding with some occasionally lost and found. It has been fun!

07211

Reposted by Stefano Esposito

Thomas Wimmer @wimmerthomas.bsky.social · 15/01/2025

We propose MET3R, a new metric for measuring multi-view consistency in generated images. Our method is built upon DUSt3R and evaluates the consistency of projected DINO features between two views. It is able to accurately capture the 3D consistency in generated images.

152

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · 15/01/2025

Excited to share that today our paper recommender platform www.scholar-inbox.com has reached 20k users! We hope to reach 100k by the end of the year.. Lots of new features are being worked on currently and rolled out soon.

1219026

Reposted by Stefano Esposito

Donato Crisostomi ✈️ NeurIPS @crisostomi.bsky.social · 08/01/2025

📢Prepend “Singular” to “Task Vectors” and get +15% average accuracy for free! 1. Perform a low-rank approximation of layer-wise task vectors. 2. Minimize task interference by orthogonalizing inter-task singular vectors. 🧵(1/6)

143

Reposted by Stefano Esposito

Rosa Ritunnano @rritunnano.bsky.social · 20/12/2024

Instead of listing my publications, as the year draws to an end, I want to shine the spotlight on the commonplace assumption that productivity must always increase. Good research is disruptive and thinking time is central to high quality scholarship and necessary for disruptive research.

211145373

Reposted by Stefano Esposito

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 18/12/2024

A short list of tips for keeping a clean, organized ML codebase for new researchers: eugenevinitsky.com/posts/quick-...

eugenevinitsky.com

Eugene Vinitsky

1213830