ETH AI Center

We’re now on Bluesky!🦋 Follow us at @ eth-ai-center.bsky.social (bsky.app/profile/eth-ai…) for updates on AI research, events, and more. See you there! #AI #ETHZurich #BLUESKY

Robotic World Model is a black-box, end-to-end learned dynamics model for general robotics. While primarily tested on rigid robots, we see its greater potential in systems with more complex dynamics. (s-a-s') Data in -> Policy out 🥳Now on Colab colab.research.google.com/drive/1SRL0ss5…

💬The upcoming AI for Good Webinar Series - with @mariotelfig (@istecnico, @itnewspt) and @ArnoutDevos (@ELLISforEurope, @ETH_AI_Center) on "The why of AI: Uncovering cause and effect in observational data" 📅 Wed, Feb 18th 🕓 16:00-17:00 CET 🔗Register: aiforgood.itu.int/event/the-why-…

Deployed LLMs and users generate millions of conversations every day. These are full of useful learning signals, yet we don't use them for training. We introduce self-distillation for learning directly from user conversations – no rewards, no labels, no extra models.

The submissions to our @CVPR workshop OpenSUN3D on Open-World 3D Scene Understanding and Representations are open! 🏔️🤖☀️ ➡️ The deadline for the proceedings track is on the 5th of March!🏃‍♀️ 🌍: opensun3d.github.io 📝: openreview.net/group?id=thecv…

🌍 World models need to know what they don't know. 📢 Our Doctoral Fellow Chenhao Li @breadli428 incorporates uncertainty into his Robotic World Model to enable real robot control. 🚀 Project: sites.google.com/view/uncertain…

Today @mimicrobotics and friends are excited to share mimic-video, a new class of Video-Action Model that elevates video model backbones as first class citizens for robot learning!

Shoutout to @jjonpai, @Liam862373, @oier_mees and the rest of the team for making this happen! @mimicrobotics @Microsoft @ETH @ETH_AI_Center @UCBerkeley @NVIDIARobotics You can find the paper website here: mimic-video.github.io

Tired of conditioning 3D generative models only through images and text? ➡️ We just released code of SpaceControl, our method to control the generation directly in 3D ✨👩‍🎨 👾: github.com/spacecontrol3d… 🌍: spacecontrol3d.github.io @FrancisEngelman @orlitany @IanHuang3D @mapo1

Are images and text enough to control 3D generative models? SpaceControl shows there’s more: we turn 3D drafts into detailed, perfectly aligned 3D assets ✨🚀 📜: arxiv.org/pdf/2512.05343 🌍: spacecontrol3d.github.io

ZurichRobotics#2 is on December 15th at the @ETH_AI_Center! Antonio Arbues @arbwes (@loki_robotics) will talk about building useful robots in the age of AI and Giacomo Manzoni (Hexagon) about imitation learning for dexterous manipulation. RSVP below, spots limited.

🌍World models are compelling to robot intelligence, yet deployment remains fragile. 📢Our Doctoral Fellow Chenhao Li (@breadli428) dives deep with his Robotic World Model and isolates the missing components blocking reliable real-world control. 🚀Project: sites.google.com/view/roboticwo…

Getting a dynamics model that is compatible with PPO's long rollouts is hard. It took us a long time to find effective yet simple tricks to make imagination rollouts less prone to hallucination. In the end, autoregressive training with backpropagation through time worked out.

Excited to share that our paper, “Can Vision-Language Models Solve Visual Math Equations?” has been accepted at EMNLP 2025! 📍 Poster Info 🗓️ Wednesday, November 5th 🕟 16:30–18:00 📌 Hall C – Main Poster 📄 Paper: arxiv.org/pdf/2509.09013 🧑‍💻 GitHub: github.com/eth-lre/MathEv…

Yesterday, we had the pleasure of hosting Prof. @SchmidhuberAI for an inspiring talk at the @ETH_AI_Center, together with our student-led partner @zurichnlp! 📈 Their talk included the history of AI, neural architectures, meta-learning, POWERPLAY, and the future with physical AI.

Thank you @SchmidhuberAI for speaking in front of a packed room at ZurichAI in the @ETH_AI_Center yesterday! It's the biggest event so far, by far. Thanks everyone for coming; we're sorry for anyone who couldn't didn't get a spot. More and bigger things are planned!

We're excited that everyone is excited about @SchmidhuberAI coming to ZurichAI at the @ETH_AI_Center tomorrow. The event is fully booked and we have limited space. Please come on time and only if you are registered. Thank you!

I'm in Switzerland next week! On Friday, October 17, I'll be giving a talk at @ETH_AI_Center on memorization in diffusion models. Please join if you're around!

🚀🤖 New survey on Multi-Agent AI for Science More and more science is driven by human collaboration, so why don’t we take inspiration and explore Multi-Agent Systems #MAS4Science as the next stage of #AI4Science? Motivation is simple: Human scientists collaborate, why not AI?🧵

📢 Excited to share our latest work @corl_conf: Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility! #CoRL2025 🐶Now ANYmal learns to walk (hop) from real dog motions! 📄Paper: arxiv.org/abs/2505.16084 🌐Project Website: anymalprior.github.io

🤖What if you want to train rough terrain humanoid locomotion but have only flat terrain demonstrations? ⛳️In ConsMimic, we introduce a principled pipeline to learn stylistic motions from demonstrations that may not align with task objectives. See you @corl_conf in Seoul!