Arno Solin

Fresh from the press: "Applied Stochastic Differential Equations" with @simosarkka and published by @CambridgeUP. Physical books: Online PDF version: Codes:

🔥 #LeAVJEPA: A simple recipe for self-supervised learning from sound and vision 🔥 One shared encoder, trained without class labels. Dropping a modality makes audio & video learn a common representation. 🧵

5/ In the video, audio-to-video attention follows the sound-producing objects, although the model received no localisation supervision. With attentive probes on frozen ViT-L features, we obtain 36.0 mAP on AudioSet-20K and 91.3% accuracy on ESC-50.

6/ Joint work with @bhrobson_, @SanteriMentu, and @wszhao_robot at ELLIS Institute Finland and Aalto University. Check out our paper, project page with interactive examples, and code: 📄 Preprint: 💻 Project page:

RT @qberthet: Submissions will open soon for #AISTATS 2027 More info (soon) at: Submission opens Sept 15th 2027 at 🌍 🕜 - Beijing: 7:30 PM - Paris: 1:30 PM - Montreal/NY: 7:30 AM - San Francisco: 4:30 AM - AOE: 11:30PM (Sept. 14th)

RT @qberthet: #AISTATS 2027 Call for Paper is out! This year's edition is taking place in Montreal on May 3-6th, 2027 🇨🇦 Aymeric Dieuleveut and I are chairing New this year: AI review, and more! Abstract deadline: September 29, 2026 Paper deadline: October 6, 2026

RT @ericmalmi: I had the privilege of sitting down with @kchonyc for our new AI podcast "And humanity created intelligence". we discussed the backstory behind the attention paper as well as... 🧵

RT @katarinaslama: I joined Aalto University's podcast "And humanity created intelligence" for an episode on AI safety, including the recent OpenAI / Hugging Face attack. Many thanks to @ericmalmi and @arnosolin for a great conversation!

🎙️Katarina Slama, ex-OpenAI, discusses AI alignment and risks in our new episode of "And Humanity Created Intelligence" -- and, for the first time, this one is in English. 1/n

We also talk about the early days of OpenAI, RLHF, and the ideas behind ChatGPT, immediate vs. catastrophic AI risks, AI consciousness and model welfare -- and, of course, p(doom). 4/n

Links to the podcast: 🎧 Spotify: 🎧 Apple Podcasts: 🎧 YouTube:

RT @zhenjun_zhao: SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis Yejun Zhang, Zihan Wang, Xu Ji, Yihao Wang, Yuxin Hou, Junyuan Fang, Juho-Matti Kilpeläinen, @arnosolin, Hamed Rezazadegan Tavakoli, Esa Rahtu, Juho Kannala tl;dr: repurpose 3DGS reconstruction as a unified interface for pixel-level rendering, feature-level token guidance, visibility-aware view selection

🎧 AI-podcastin "Ja ihminen loi älyn" 2. jakso on ulkona. Vieraana emeritusproffa Erkki Oja, joka kehitti neuroverkkoja jo ennen kuin ne olivat tekoälyn valtavirtaa. 1/2

Ja ihminen loi älyn -podcastissa mulla ja @ericmalmi tavoitteena on päästää ääneen suomalaisia ja Suomi-taustaisia tekoälyalan kiinnostavia hahmoja. 2/2 🎧Spotify: 🎧Apple Podcasts: 🎧YouTube:

Today I turn 40. 🎂 Four decades in, I still find myself doing what I enjoy most: learning new things, building ideas, and working with talented people on problems that were still science fiction when I was born.

Thanks to family, friends, colleagues, and students who have been part of the journey so far. 🤗