Arno Solin
Associate Professor in Machine Learning, Aalto University. ELLIS Scholar.
http://arno.solin.fi
- Statement from #AISTATS2026 organizers regarding the @openreview.bsky.social API Security Incident
- OpenReview's announcement: openreview.net/forum/user%7...
- I recently gave my installation talk after being tenured. The video of the talk is now available on the university's YouTube channel: youtu.be/R1UQoflPTDg 1/n
- I talked about "Making Sense of Learning Machines": • How modern machine learning has learned to cope with natural, “chaotic” data – images, text, sound • Why the big breakthroughs of the last 10–15 years matter • What we lack and what we would like to understand 2/n
- My own research, together with my group, focuses less on building the giant models and more on designing the building blocks behind them: model components, inductive biases, training principles, and inference methods that make AI systems more robust, data-efficient, and uncertainty-aware. 3/n
- I'm feeling grateful to colleagues, students, collaborators, and everyone who joined the talk – and excited about the next steps in research on machines that learn, and maybe one day, truly make sense. 🙏✨ 4/n
- 📣 Please share: We invite submissions to the 29th International Conference on Artificial Intelligence and Statistics (#AISTATS 2026) and welcome paper submissions at the intersection of AI, machine learning, statistics, and related areas. [1/3]
- Accepted papers will be presented in person in Morocco, May 2–5, 2026. The full Call for Papers is available here: virtual.aistats.org/Conferences/... [2/3]
- I'm thrilled to be Program Chairing AISTATS 2026 together with Aaditya Ramdas. AISTATS has a special feel to it, and it has been described by many colleagues as their "favourite conference". We aim to preserve that spirit while introducing some fresh elements for 2026. [3/3]
- Reposted by Arno SolinRemember that computers use bitstrings to represent numbers? We exploit this in our recent @auai.org paper and introduce #BitVI. #BitVI directly learns an approximation in the space of bitstring representations, thus, capturing complex distributions under varying numerical precision regimes.
- Real-world #3DGS scenes are messy—occluders, moving objects, and clutter often ruin reconstruction. This #CVPR2025 paper presents DeSplat, which separates static scene content from distractors, all without requiring external semantic models. [1/n]
- Compared to Splatfacto we model and can ignore distractors to improve 3DGS reconstruction quality. [2/n]
- Qualitative visualization of static distractor elements achieved by our model, DeSplat. [3/n]
- Check our #CVPR paper and project page for more results, videos, and code! 📄 arxiv.org/abs/2411.19756 🎈 aaltoml.github.io/desplat/
- I’m visiting the Isaac Newton Institute for Mathematical Sciences in Cambridge this week. I’m giving an invited talk in the ”Calibrating prediction uncertainty : statistics and machine learning perspectives” workshop on Thursday.
- Have you thought that in computer memory model weights are given in terms of discrete values in any case. Thus, why not do probabilistic inference on the discrete (quantized) parameters. @trappmartin.bsky.social is presenting our work at #AABI2025 today. [1/3]
- We introduce BitVI, a novel approach for variational inference with discrete bitstring representations of continuous parameters. We use a deterministic probabilistic circuit structure to model the distribution over bitstrings, allowing for exact and efficient probabilistic inference. [2/3]
- Our method addresses the eminent question of probabilistic modelling in quantized large-scale ML models. See the workshop paper below. [3/3] 📄 Paper: openreview.net/forum?id=Sai...
- Excited to share "Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation", presented at the #ICLR2025 "Workshop on Reasoning and Planning for LLMs" on Monday! 🚀 1/3
- This work was born out of Prakhar's internship with Microsoft Research (\w Sukruta Prakash Midigeshi, Gaurav Sinha, Arno Solin, Nagarajan Natarajan, and Amit Sharma). 2/3
- We show that externalising reasoning as a DAG at test time leads to more accurate, efficient multi-hop retrieval – and integrates seamlessly with RAG systems like Self-RAG. 📄 Paper: openreview.net/pdf?id=gi9aq... 3/3
- Our TMLR-to-ICLR poster "Exploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision Matrices" (Frida Viset, Anton Kullberg, Frederiek Wesel, Arno Solin) 🗓️ Hall 3 + Hall 2B #416, Fri 25 Apr 10 a.m. +08 — 12:30 p.m. +08 📄 Preprint: arxiv.org/abs/2408.02346
- Our #ICLR2025 poster "Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models" (Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg) 🗓️ Hall 3 + Hall 2B #194, Fri 25 Apr 3 p.m. +08 — 5:30 p.m. +08 📄 Preprint: arxiv.org/abs/2405.17656
- Our #ICLR2025 poster "Streamlining Prediction in Bayesian Deep Learning" (Rui Li · Marcus Klasson, Arno Solin, Martin Trapp) 🗓️ Hall 3 + Hall 2B #413, Fri 25 Apr 10 a.m. +08 — 12:30 p.m. +08 📄 Preprint: arxiv.org/abs/2411.18425
- Our #ICLR2025 poster "Discrete Codebook World Models for Continuous Control" (Aidan Scannell, Mohammadreza Nakhaeinezhadfard, Kalle Kujanpää, Yi Zhao, Kevin Luck, Arno Solin, Joni Pajarinen) 🗓️ Hall 3 + Hall 2B #415, Thu 24 Apr 10 a.m. +08 — 12:30 p.m. +08 📄 Preprint: arxiv.org/abs/2503.00653
- Our #ICLR2025 poster "Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs" (Severi Rissanen, Markus Heinonen, Arno Solin) 🗓️ Hall 3 + Hall 2B #140, Thu 24 Apr 3 p.m. +08 — 5:30 p.m. +08 📄 Preprint: arxiv.org/abs/2410.11149
- This week, we are presenting five papers at the main conference of the Thirteenth International Conference on Learning Representations (#ICLR2025) in Singapore. You can find my research group members and collaborators at the following posters.
- Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs Severi Rissanen · Markus Heinonen · Arno Solin Hall 3 + Hall 2B #140 🗓️ Thu 24 Apr 3 p.m. +08 — 5:30 p.m. +08 📄 arxiv.org/abs/2410.11149
- Discrete Codebook World Models for Continuous Control Aidan Scannell · Mohammadreza Nakhaeinezhadfard · Kalle Kujanpää · Yi Zhao · Kevin Luck · Arno Solin · Joni Pajarinen Hall 3 + Hall 2B #415 🗓️ Thu 24 Apr 10 a.m. +08 — 12:30 p.m. +08 📄 arxiv.org/abs/2503.00653
-
View full threadExploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision Matrices Frida Viset · Anton Kullberg · Frederiek Wesel · Arno Solin Hall 3 + Hall 2B #416 🗓️ Fri 25 Apr 10 a.m. +08 — 12:30 p.m. +08 📄 arxiv.org/abs/2408.02346
- There is still time to submit your papers to our #CVPR2025 workshop on Uncertainty Quantification for Computer Vision, which is part of the workshop lineup at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) in Nashville, Tennessee.
- We accept both regular papers (that will follow the CVPR format, published in proceedings) and extended abstracts (short max 4-page papers, not published in proceedings). Submission deadline: March 14th, 2025.
- More information: uncertainty-cv.github.io/2025/
- Reposted by Arno SolinAre you going to be at #WACV and want to know if “Flatness Improves Backbone Generalisation in Few-shot Classification”? Then join the oral presentation by @ruili-pml.bsky.social of our paper! 🔗 lnkd.in/dBMmN7Vs Done together with @marcusklasson.bsky.social and @arnosolin.bsky.social.
- This week I have been teaching ML outside my own academic bubble. 🫧 I have been giving a crash course as part of the #Nordita Winter School on "Physics of Machine Learning & Machine Learning for Physics“ in Stockholm. Great interaction with young physicists and new avenues for applying ML. ✨
- I also stumbled upon the “Classical Mechanics Lab” (in the picture), and physics labs sure are different than I thought.
- 🔥Great workshop! — #NeurIPS workshop on Bayesian Decision-making and Uncertainty. \w @trappmartin.bsky.social
- On Wednesday, Oliver Hamelijnck (with Theo Damoulas and me) is presenting our paper "Physics-Informed Variational State-Space Gaussian Processes" at NeurIPS in Vancouver. Come by poster 4204 in East Exhibit Hall A-C starting 11 am. 📝 Paper pre-print: arxiv.org/abs/2409.13876
- Reposted by Arno SolinI will present ✌️ BDU workshop papers @ NeurIPS: one by Rui Li (looking for internships) and one by Anton Baumann. 🔗 to extended versions: 1. 🙋 "How can we make predictions in BDL efficiently?" 👉 arxiv.org/abs/2411.18425 2. 🙋 "How can we do prob. active learning in VLMs" 👉 arxiv.org/abs/2412.06014
- I will be at #NeurIPS2024 in Vancouver. I’m looking for post-docs, and if you want to talk about post-doc opportunities, get in touch. 🤗 Here’s my current team at Aalto University: users.aalto.fi/~asolin/group/
- Reposted by Arno SolinDeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering Yihao Wang, Marcus Klasson, Matias Turkulainen, Shuzhe Wang, Juho Kannala, @arnosolin.bsky.social tl;dr: decompose alpha compositing and explicitly separate occluders and the underlying static 3D scene arxiv.org/abs/2411.19756
