Thrilled to announce my election to the National Academy of Engineering (@theNAEng ). I am grateful for the support of my @PennEngineers colleagues, mentors, and above all, my students and postdocs that have made this distinction possible.

When humans and AI collaborate, what should uncertainty quantification look like? Our new paper proposes two principles---no counterfactual harm and complementarity---and gives distribution-free guarantees without assumptions on the task, AI model, or human behavior.

As LLMs advance, researchers are testing how they interact with the physical world. Prof. @pappasg69 (@ESEatPenn, @MEAM_Penn, @cis_penn) said, “LLMs can now instruct robots on tasks,” but true autonomy will require learning through real-world interaction. https://t.co/dSpdZhGGA2

How should you use forecasts f:X->R^d to make decisions? It depends what properties they have. If they are fully calibrated (E[y | f(x) = p] = p), then you should be maximally agressive and act as if they are correct --- i.e. play argmax_a E_{o ~ f(x)}[u(a,o)]. On the other hand

I will be presenting on this work at @INFORMS2025 in Atlanta on Tuesday, October 28, 4:15-5:30 pm, in the Machine Learning and Optimization session (Building B, Level 2, Room B208)!

Congratulations to @pappasg69, recipient of the Test of Time Award at RV 2025 for the paper “Robustness of Temporal Logic Specifications,” co-authored with Georgios E. Fainekos. Pappas is the UPS Foundation Professor of Transportation in @ESEatPenn, @MEAM_Penn and @cis_penn.

Penn hosted (@FrontiersNAE) for the first time, for the nation's most promising early-career engineers to discuss the future of fields from quantum computing to fusion energy. Thank you to sponsors The Grainger Foundation, IBM, Penn's Office of the Vice Provost for Research,

Congratulations to @PennEngineers and @PennEngAI's George Pappas on his 2025 @IEEEorg Leon K. Kirchmayer Graduate Teaching Award, sponsored by @ieeecassociety, @IEEEembs, and @IEEEsps. Learn more about his work and #mentorship in this Q&A: https://t.co/PnknGx8gKU #IEEEAwards2026

If you are in Athens this weekend, there is only one place to be (and no, I’m not referring to the beach). Greeks in AI 2025, the annual gathering of the most amazing Greek AI scientists and practitioners, will take place on 19-20 July. An event not to be missed!

This is such a special award. It really recognizes how outstanding my doctoral students and postdocs are. I am deeply honored. Thanks @IEEEorg

Congratulations to George Pappas (@pappasg69) on receiving the 2025 @IEEEorg Leon K. Kirchmayer Graduate Teaching Award. With over two decades of educating at Penn, Pappas is recognized for his "inspirational mentoring" of graduate students.

We push conformal prediction and its trade-offs beyond regression & classification — into query-based generative models. Surprisingly (or not?), missing mass & Good-Turing estimators emerge as key tools once again. Very excited about this one!

Tired of the aggressive mediocrity of robust control (RC) and the unreliability of certainty equivalent (CE) control?! Then try domain randomization (DR)! We prove that DR-based control of an unknown linear system is nearly as efficient as CE control, and nearly as reliable as RC

Wondering how to make high-stakes decisions using ML—in areas like medicine, robotics, or finance? Our latest work lays out a decision-theoretic foundation for risk-averse uncertainty quantification. If you want to learn how to make better calls when it truly matters, read on!

Paper here: https://t.co/cNfXOcEcfF Joint work with the excellent @ShayanKiyani1 @pappasg69 and @HamedSHassani

What are prediction sets good for? It turns out just as calibration is the "right" way of quantifying uncertainty for risk-neutral (expectation maximizing) decision makers, prediction sets are the right way of quantifying uncertainty for risk-averse decision makers.

🔥🔥🔥 Adversarial reasoning is born. Hot take: The core problem we address in this paper is the role of reasoning in AI safety. While there have been recent efforts by @OpenAI arguing that replacing reasoning with increased compute can lead to better defense mechanisms, these

Security researchers tested 50 well-known jailbreaks against DeepSeek’s popular new AI chatbot. It didn’t stop a single one.

A new generation of jailbreaks are rolling out by our team at @robusthq and in collaboration with @PennEngineers. We jailbreak @deepseek_ai R1 model with a %100 attack success rate. To know more, see our blog post on @CiscoSecure and the corresponding @WIRED article. amazing

Congrats to @pappasg69 & @NikolaiMatni for winning the 2024 @CSSIEEE Best Paper Awards. Their research advances safety and control systems for AI and large-scale applications. @ESEatPenn, @CIS_Penn, @MEAM_Penn, @PennEngineers https://t.co/JW1TzdyyTj

Excited to win the George Axelby Award from the IEEE Control Systems Society with @MFazlyab and Manfred Morari. Even more excited @NikolaiMatni won the best paper at IEEE Transactions on Control of Networked Systems at @IEEECDC2024 @PennEngineers https://t.co/mWDjci33qM