Center for Safe, Explainable, and Trustworthy AI

A @PennEngineers research center devoted to science and tools for ensuring AI-enabled systems are safe, explainable, and trustworthy

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you to Rene Vidal for giving our final ASSET seminar presentation of this semester! If you missed his talk you can view the recording here: https://t.co/njkvEGxTdm

[Rabdos_AI @Rabdos_AI]

Static math benchmarks saturate. We built one that doesn't.

Announcing MathDuels, the first self-play math benchmark.

Every frontier LLM writes problems for the others, and is graded on the ones written for it. As models improve, so does the benchmark.

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Join us tomorrow for our final ASSET Seminar of this semester, presented by Rene Vidal (UPenn). See below for details!

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you @LingjieLiu1 for presenting at this week's ASSET Seminar! If you missed her talk, you can view the recording here: https://t.co/LMnjPoNPJB

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Join us tomorrow for an ASSET Seminar by @LingjieLiu1: "Beyond Photorealism: 3D Reconstruction and Generation with Multimodal and Physical Grounding". See below for more details!

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you to Misha Belkin for visiting Penn yesterday to present for this week's ASSET Seminar! If you missed his talk, you can view the recording here: https://t.co/yQy3IkLgT1

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

We hope you will join us for tomorrow's ASSET Seminar presentation by Misha Belkin (UC San Diego): “From kernel machines to the linear representation hypothesis for monitoring and steering LLMs”! See below for more details:

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Congratulations to the twelve ASSET Center PhD students who were named 2026 AWS Fellows! Read more about the fellows and their research on our website: https://t.co/QtWeKA1yq4

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you @vitercik for presenting at yesterday's ASSET Seminar! If you missed her talk you can view the recording here: https://t.co/CN6ZzJg4cQ

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

We are thrilled to welcome Ellen Vitercik (@vitercik) from Stanford as tomorrow's ASSET Speaker! Please see below for more details about this week's seminar:

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you again to Nika Haghtalab for visiting the ASSET Center to give a presentation! If you missed her talk you can view the recording here: https://t.co/w4RAUAnm2j

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Please join us tomorrow for an ASSET Seminar presentation by Nika Haghtalab from UC Berkeley on Distortion of AI Alignment from Human Feedback! See below for more details:

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you to Sandeep Chinchali for an engaging seminar presentation yesterday! If you missed his talk you can view the recording here: https://t.co/sPVZfntdmf

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Join us tomorrow for an ASSET Seminar by Sandeep Chinchali from UT Austin on "Why We Need Multimodal Generative AI for Time Series (and Video)"! See below for details:

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you to Anjalie Field for giving a fascinating talk yesterday! If you missed it, you can view the recording of her seminar here: https://t.co/AJx60VcyW5

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

For this week's ASSET Seminar we will hear from Anjalie Field of JHU addressing the question: "How can we enable LLM auditing?" See below for details on tomorrow's talk!

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you to @amritsinghbedi3 for presenting at yesterday's ASSET seminar! If you missed his talk you can view the recording here:
https://t.co/p9wTb2xq60

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

We are delighted to welcome @amritsinghbedi3 to Penn for this week's ASSET Seminar tomorrow! Please see below for more details and we hope you can join!

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Thank you to Yuanyuan Shi for presenting at last week's ASSET Seminar! If you missed her talk, you can view the recording here: https://t.co/ExWKubddVj

[Center for Safe, Explainable, and Trustworthy AI @PennAsset]

Join us tomorrow for an ASSET Seminar presentation by Yuanyuan Shi from UC San Diego on Reliable Physical AI for Power Systems: Stability-Constrained Reinforcement Learning and Generative Lyapunov Function Discovery.