@chriswolfvision.bsky.social
Principal Scientist at Naver Labs Europe, Lead of Spatial AI team. AI for Robotics, Computer Vision, Machine Learning. Hobby Cyclist. Austrian in France. https://chriswolfvision.github.io/www/
@chriswolfvision.bsky.socialCan we make an exception for 2 very specific people though? You know exactly who I mean.
@dimadamen.bsky.socialReposted by @chriswolfvision.bsky.socialIt is the *best* time to start your own research group in AI
@compscibristol.bsky.social
Why?
🌟 Bristol hosts the largest supercomputer in the UK - Isambard AI, 4th greenest in the world.
🧑🎓 New undergrad degree CS w AI &multiple masters
6⃣ Nov DL to apply for position, Link in 🧵
@chriswolfvision.bsky.socialHow is that different from what happens in, say, Washington DC, especially now?
@chriswolfvision.bsky.socialI don't understand why we would want to restrict ourselves to Europe. And the Wero does already that, in Europe. We need a global payment system which cannot arbitrarly shut out people and orgs which are politically inconvenient. It needs to be global.
@chriswolfvision.bsky.socialI am not an expert but isn't the digital Euro supposed to do exactly that?
@chriswolfvision.bsky.socialWhatever you think of what happens in geopolitics lately, it has a really good side effect on Europe's efforts to create and to push its own global payment system. Which cannot be sanctioned (and whose benefits stay in the region).
@chriswolfvision.bsky.socialI thought you meant Piranesi. I am so disappointed now.
@chriswolfvision.bsky.socialThat's actually exactly what I do.
@chriswolfvision.bsky.socialOMG this saves so much time. I have my own Jarvis now.
@chriswolfvision.bsky.socialMe: writing the paper on overleaf Claude: sidekick, ready to do reformatting, layout, eg. remove white space in front of each paragraph; integrate figure; use tikz to overlay text.
@chriswolfvision.bsky.socialFunnily (hum...) all presentations and figures now look a like and have the same style.
@chriswolfvision.bsky.socialHi! It's not open source, but if you DM me (or reply) I can add deadlines.
@chriswolfvision.bsky.socialRecurrent Looped Transformer
Zhang et al.
Combine context/history transformer with recurrence: have a causal encoder with a recurrent decoder.
@chriswolfvision.bsky.socialLooking forward to it 😀
@chriswolfvision.bsky.socialI am registered for the Paris venue of NeurIPS 2026! See you there 😀
@neuripseurope.bsky.socialReposted by @chriswolfvision.bsky.socialWe welcome all authors of accepted NeurIPS papers who chose the Paris venue. We are excited and working hard to make this a great event! Registrations for authors are not yet open but be reassured that 1 place is reserved for the presenter of each paper accepted to the main conf. WS authors: 1/2
he cannot be trusted outside so he gets the harness
@aemond.wsocial.euReposted by @chriswolfvision.bsky.socialLe Chonk is here 🐱 Mistral's Large 4 is a 1 trillion parameter model trained in its own European data centres, with open weights coming on 27 October. Looking at the benchmarks, it's up there with the best open models. It even does a bit better than GPT-6 Astra on some aspects. Bien joué, Mistral !
@chriswolfvision.bsky.socialProcedural Core: A Compact Recurrent Initialization for Vision Transformers
By @damienteney.bsky.social 's group
Idea: train a ViT with parameters tied over layers (="recurrent ViT") on abstract procedurally data. Then initialise models of ANY arch (!) with these weights.
@chriswolfvision.bsky.socialYou mean the ECCV'26 work involving also M. Black? I don't think there is any relationship, neither in application (we do map-free pose estimation and streaming VQA) nor in technique (we distill context transformers into recurrent transformers). Here Blender has only be used for the illustration.
