Reposted by Chris OffnerYining Karl Li @yiningkarlli.bsky.social · 29/03/2026Huge props to Lord and Miller for stepping up and doing what directors like Nolan are too cowardly to do: be up front and give loud and generous credit to their VFX team. Great directors don’t need to lie about how their movies are made; the work speaks for itself. 1223
Chris Offner @chrisoffner3d.bsky.social · 29/03/2026Any idea why Scholar Inbox cannot find the paper arxiv.org/abs/2512.11508? @si-cv-graphics.bsky.social @andreasgeiger.bsky.social 120
Reposted by Chris OffnerRyan Moulton @moultano.bsky.social · 17/03/2026If you want me to consider reading something, you have to convince me that you care way more than I do. 1746
Reposted by Chris OffnerEugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 14/02/2026All the "you need to learn AI skills or you'll get left behind" things are patently nonsense. It's easy to use and only becomes easier to use over time. If there's skill it's in knowing what it does well and what is does poorly 429817
Reposted by Chris OffnerTim Crane @timcrane.bsky.social · 11/12/2025This is a really good point. While there are men and women on the 'sceptic' side of all these debates, I don't know of any women on the AI 'booster' side. It's really a guy thing 5272
Reposted by Chris OffnerEric Brachmann @ericbrachmann.bsky.social · 17/10/2025Looking forward to a busy #ICCV2025. I will give three (very different) talks at workshops and tutorials, see info below. We also present two papers, ACE-G and SCR Priors. And it's the 10th (!) anniversary of the R6D workshop, which we co-organize. 1124
Reposted by Chris OffnerAndreas Geiger @andreasgeiger.bsky.social · 01/10/2025#TTT3R: 3D Reconstruction as Test-Time Training TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required! 🔗Page: rover-xingyu.github.io/TTT3R We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D! 0384
Reposted by Chris OffnerEuropean Commission @ec.europa.eu · 06/09/2025🚀 Europe’s first exascale supercomputer is here! JUPITER, launched in Germany, is the EU’s most powerful system and fourth fastest worldwide. 100% powered by renewables, it has also ranked first in energy efficiency. It will boost AI, science, and climate research. Read more - europa.eu/!vcWBqW 1122652
Reposted by Chris OffnerRyan Moulton @moultano.bsky.social · 05/09/2025There is a lot to hate about the politics of the silicon valley right, but they do actually want to build stuff, and I would prefer if the left didn't cede "we should be able to build stuff" to the right. 27426416
Reposted by Chris OffnerKeenan Crane @keenancrane.bsky.social · 29/08/2025I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder. The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly? 1115925
Chris Offner @chrisoffner3d.bsky.social · 23/08/2025Great video on the convergent evolution from hierarchical military command structures to cybernetics to centralized AI coordination across political ideologies: www.youtube.com/watch?v=mayo... 120
Reposted by Chris OffnerJohan Edstedt @parskatt.bsky.social · 22/08/2025In general I think 3D vision would do well to take some inspiration from Bayesians. I guess these days they lost their glamour, but imo it's a very nice way of thinking that feels somewhat lost currently. 221
Chris Offner @chrisoffner3d.bsky.social · 22/08/2025"It is beautiful. It is elegant. Does it work well in practice? Not really. This is often the caveat we face in research: the things that are beautiful don't work and the things that work are not beautiful." – Daniel Cremers 2365
Chris Offner @chrisoffner3d.bsky.social · 21/08/2025"As roboticists and computer vision people [outside of big tech], do we have to just wait for the next foundation model?" I share the frustration. It's disempowering when most major progress recently is downstream of "foundation models" that you don't have the compute or data to train yourself. 5242
Reposted by Chris OffnerBibliome @handle.invalid · 20/08/2025We're live on bluesky! bibliome.club is the platform for creating, collaborating on and sharing reading lists with your Bluesky network - open source and decentralised via ATProto.bibliome.clubBibliome - Building the very best reading lists, togetherCreate collaborative bookshelves, discover new books, and build reading communities with friends. Join the decentralized reading revolution powered by Bluesky. 724370
Chris Offner @chrisoffner3d.bsky.social · 14/08/2025Yay, DINOv3 is out! SigLIP (VLMs) and DINO are two competing paradigms for image encoders. My intuition is that joint vision-language modeling works great for semantic problems but may be too coarse for geometry problems like SfM or SLAM. Most animals navigate 3D space perfectly without language. 1315
Chris Offner @chrisoffner3d.bsky.social · 12/08/2025What are the best resources to learn about VLMs? Papers, tutorials, courses, blog posts, whatever is good. I can read the Kimi-VL or GLM tech reports and follow the breadcrumbs but I'd appreciate any and all recommendations towards a useful VLM curriculum! 🙏 182
Reposted by Chris OffnerSiobhán @shibbi.me · 28/06/2025Ensuring the robots can’t take our jobs by teaching the robots functional programming 0113
Reposted by Chris OffnerEric Brachmann @ericbrachmann.bsky.social · 23/06/2025I was not aware that the #ECCV2024 oral recordings are publicly available... So here is the #ACEZero talk: eccv.ecva.net/virtual/2024... 3282
Reposted by Chris OffnerChristian Wolf @chriswolfvision.bsky.social · 06/06/2025DUNE is a great universal image encoder which works for a large class of tasks and beats its teacher MASt3R on map free localization. #cvpr2025 We use it a lot already, I recommend it. (keynote @ Paris by @dlarlus.bsky.social ) 2435
Reposted by Chris OffnerBart Wronski 🇺🇦🇵🇸 @bartwr.bsky.social · 01/06/2025I agree 100%. It's one thing to criticize corporate practices, the social impact, ethics, or future risks. But I watch in total awe how it writes in a few seconds a well documented program in a language/API I don't know, while they complain "but it might have a bug and requires a pass or two" O_o 9344
Chris Offner @chrisoffner3d.bsky.social · 31/05/2025My X feed's reaction to Dario Amodei's recent interviews. 020
Reposted by Chris OffnerWesley Finck @wesleyfinck.org · 30/05/2025Collective intelligence is only as strong as our collective attention. 093
Chris Offner @chrisoffner3d.bsky.social · 30/05/2025Nice demonstration of the capabilities and failures of videogen models. youtu.be/US2gO7UYEfYyoutu.beWe Tested Google Veo and Runway to Create This AI Film. It Was Wild. | WSJYouTube video by The Wall Street Journal 040
Chris Offner @chrisoffner3d.bsky.social · 20/05/2025Depending on who you talk to, a “deep dive” can mean spending seven years leading a field of research, or it can mean having six words on a slide instead of two. 292
Chris Offner @chrisoffner3d.bsky.social · 19/05/2025Ambitious projects are happening in Zurich’s AI scene. www.theverge.com/news/669238/... 060
Reposted by Chris OffnerTed Underwood @tedunderwood.com · 12/05/2025This pattern is going to repeat in one domain after another, and gradually force us to admit that 60% of every job is networking, knowing who to trust, and doing poorly justified risk/benefit assessment. 2709
Reposted by Chris OffnerGiorgos Tolias @gtolias.bsky.social · 11/05/2025VRG from CTU in Prague has 9 of its members listed as outstanding reviewers. Congratulations to @gkordo.bsky.social, @billpsomas.bsky.social , @stojnicv.xyz , Pavel Suma, @ducha-aiki.bsky.social , Miroslav Purkrábek, Tomas Vojir, and Yaqing Ding. 0173
Reposted by Chris OffnerETH CS Department @csateth.bsky.social · 08/05/2025🎉💡 Impressions from today’s ETH Augmented Reality Lab (ETHAR) opening, a new hub dedicated to advancing core technologies in AR, in collab with Google. scientists.@christianholz.bsky.social @ethzurich.bsky.social 061
Reposted by Chris OffnerETH Zurich @ethz.ch · 09/05/2025What happens when ETH Zurich teams up with Google to shape the future of #AugmentedReality? We're opening a new #Researchhub that brings together top minds to tackle one of the biggest challenges in tech: seamlessly blending the digital and physical worlds. Read more:ethz.chMaking augmented reality suitable for societyETH Zurich is establishing a new research hub for augmented reality that involves close collaboration with Google. One of the ETH-Co-heads, Christian Holz, explains the importance of networking in thi... 194
Reposted by Chris Offnerpablovelagomez.bsky.social @pablovelagomez.bsky.social · 02/05/2025Trying to wrap my head around fwd/bwd kinematics for imitation learning, so I built a fully‑differentiable kinematic hand skeleton in JAX and visualized it with @rerun.io new callback system in a Jupyter Notebook. This shows each joint angle and how it impacts the kinematic skeleton. 172
Reposted by Chris OffnerMark Pauly @markpauly.bsky.social · 02/05/2025Please share widely: The EPFL Geometry Computing Laboratory is launching its third call for an Artist / Designer Residency for the fall of 2025! More information on how to apply here: www.epfl.ch/labs/gcm/ope... #design #art #residency #research 02013
Chris Offner @chrisoffner3d.bsky.social · 02/05/2025kids these days, am I right? @clairebraeuer.bsky.social 1130
Reposted by Chris OffnerParker Butler @parkerbutler.bsky.social · 30/04/2025Just incredible 1394280928988
Reposted by Chris OffnerJacques Lucke @jacqueslucke.bsky.social · 01/05/2025I wrote a document describing how we want to make it possible to build high level and easy-to-use node group assets for physics simulations and more. #b3d #devfund #GeometryNodes devtalk.blender.org/t/declarativ...devtalk.blender.orgDeclarative Systems in Geometry NodesCurrently, one of our primary goals for Geometry Nodes is to get to a point where we can build high level and easy to use node group assets for physics simulations. Our general approach was described… 0296
Reposted by Chris OffnerJon Barron @jonbarron.bsky.social · 28/04/2025Here's a recording of my 3DV keynote from a couple weeks ago. If you're already familiar with my research, I recommend skipping to ~22 minutes in where I get to the fun stuff (whether or not 3D has been bitter-lesson'ed by video generation models) www.youtube.com/watch?v=hFlF...youtube.comRadiance Fields and the Future of Generative MediaYouTube video by Jon Barron 25912
Chris Offner @chrisoffner3d.bsky.social · 29/04/2025“GPT-image feedback loop, asking the machine to replicate the image without changing anything.” (from x.com/indian_brons...) 6465
Reposted by Chris OffnerFrançois Fleuret @francois.fleuret.org · 28/04/2025I asked "on the other platform" what were the most important improvements to the original 2017 transformer. That was quite popular and here is a synthesis of the responses: 420643
Chris Offner @chrisoffner3d.bsky.social · 28/04/2025“The final frontier is not space — it’s status.” www.slater.works/posts/post-s...slater.worksThe Eternal Pageantry of the Post-Scarcity MindPost-scarcity science fiction tends to be low interpersonal conflict. In the Walle-E dystopia, everyone is fat and lazy, nobody is fighting or striving. In Star Trek and the Culture series, the confli... 220
Chris Offner @chrisoffner3d.bsky.social · 28/04/2025Wisdom is knowing when to rely on science and when to believe in a bit of magic. Tonight it’s time for the Böögg! 061
Reposted by Chris OffnerAlexander Doria @dorialexander.bsky.social · 27/04/2025The unfortunate reality is that open ai research community has solidified on the bad site over the past few months. Much more ties, ongoing collaborations on group chats, irl meetups, larger audience (especially post-DeepSeek effect). 3305
Reposted by Chris OffnerEthan Mollick @emollick.bsky.social · 26/04/2025This was helpful. Also worth noting that Bluesky remains a very fraught place for AI discussions for a variety of reasons, good & bad, but with the impact of keeping a lot of the most relevant AI news, paper discussions & biggest names on X That might change, but it hasn’t yet. Still posting, tho. 1224117
Chris Offner @chrisoffner3d.bsky.social · 26/04/2025I guess she should’ve worked on Grok instead. techcrunch.com/2025/04/25/a... 290
Reposted by Chris OffnerAnton Obukhov @obukhov.ai · 25/04/2025The workshop report is now released! arxiv.org/abs/2504.17787 121
Chris Offner @chrisoffner3d.bsky.social · 24/04/2025Can’t wait to read Tim Apple’s “The Art of the Deal” www.theverge.com/news/654882/...theverge.comDid Tim Cook finagle a special tariff deal? Senator Warren wants to knowSenator Warren sent a letter to Cook. 020
Chris Offner @chrisoffner3d.bsky.social · 23/04/2025China Has an Army of Robots on Its Side in the Tariff War www.nytimes.com/2025/04/23/b... 020
Reposted by Chris OffnerYining Karl Li @yiningkarlli.bsky.social · 23/04/2025Pretty cool seeing visionOS support to Godot. In general it’s been nice seeing Apple make major contributions recently to Blender and various other open source graphics projects. The orange website comments are a bummer though; don’t read them. github.com/godotengine/...github.comNative visionOS platform support by rsanchezsaez · Pull Request #105628 · godotengine/godotDear Godot community, I'm on Apple's visionOS engineering team, and we would like to contribute Vision Pro support to the Godot engine. This is the first PR that lays the foundation for tha... 2102