Assistant Professor of Algorithmic Systems Theory @ETH_en. Interested in everything that moves autonomously! Previously @USC, @Penn, @KTHuniversity and @kielu.
Los Angeles
Joined November 2020
- Tweets250
- Following372
- Followers1.5K
- Likes1.1K
Thanks for the invitation @mahdisoltanol - it was great being back!
Next time I'll make sure to follow the rules 😎
Great to have @LarsLindemann2 back this week. He kicked off the AIF4S seminar on Friday with a great talk on “safe control under distribution shifts with robust conformal prediction” more detail: sites.usc.edu/aif4s/cool_tim…
@ult_flymachine just joined my new lab at ETH and directly dropped an absolute brick of a paper: arxiv.org/pdf/2511.10586 🚀The paper addresses interaction-induced distribution shifts in interactive environments via iterative policy updates and adversarial conformal prediction.
This adjustment is performed based on a policy-to-trajectory sensitivity analysis, resulting in a safe, episodic planner. We further conduct a contraction analysis of the system providing conditions under which both the CP results and the policy updates are guaranteed to converge
🚨 Reminder: 45 days left to submit to L4DC 2026! 🚨
We encourage all researchers to submit their work to the Learning for Dynamics & Control Conference (L4DC 2026) which will take place at USC in Los Angeles between June 17–19, 2026.
🗓️ Paper submission deadline: Nov. 8, 2025
Lars Lindemann retweeted
Check out our approach to 𝐬𝐚𝐟𝐞𝐭𝐲 𝐩𝐫𝐞𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 , where we pretrain 2B models from scratch on filtered web data to be safe by construction 🚀
Last Gold’s workout with @mahdisoltanol 💪🏻💪🏻💪🏻
Last training session with coach @LarsLindemann2 before his ✈️ to Zurich. There is an opening for a USC colleague to serve as my coach. Any interest @Schwarzenegger?
Lars Lindemann retweeted
Last training session with coach @LarsLindemann2 before his ✈️ to Zurich. There is an opening for a USC colleague to serve as my coach. Any interest @Schwarzenegger?
Don't forget to sign up for our CDC workshop on "Neurosymbolic Control for Verifiable Design of AI-Enabled Systems" before the early registration deadline on Sep. 3rd. You can find the program under sites.google.com/view/cdc4ne… and sign up directly via cdc2025.ieeecss.org/registra… 🚀
We’re excited to host the 8th Learning for Dynamics & Control (L4DC) Conference at the University of Southern California from June 17–19, 2026 ☀️🌴
Consider submitting your latest research at the interface between learning, optimization, and control, see sites.google.com/usc.edu/l4d…
We spent some time thinking about how to express and verify spatial and temporal properties for distributed systems and came up with STL-GO, a spatio-temporal logic with graph operators. Check out @ZhaoYiqi87035 work if you're curious 🙂
We are happy to share our recent work (appearing in EMSOFT '25) named "STL-GO: Spatio-Temporal Logic with Graph Operators for Distributed Systems with Multiple Network Topologies": arxiv.org/abs/2507.15147, focusing on distributed monitor of dynamic multigraphs across topologies.
Today is the day: our RSS workshop on "Statistical Uncertainty Quantification in the Era of AI-Enabled Robots" is starting soon 😊 If you are attending RSS, drop by and say hi. Otherwise, join us online via zoom (details can be found here sites.google.com/view/rss202…). See you soon!
Attending RSS at USC next week? We are organizing a workshop on "Statistical Uncertainty Quantification in the Era of AI-Enabled Robots" and have a fantastic lineup of speakers from academia and industry: sites.google.com/view/rss202…. Looking forward to seeing many of you 😎
I gave an in-depth tutorial on "Formal Verification and Control with Conformal Prediction" at KTH today 🚀 Since I got positive feedback, I wanted to share the presentation, in the hope that others can also benefit from it 🙂 Find the recording here: youtu.be/kfPBjaMCXmM?si=0Y9O…