Weekly Media Update

Week of June 12, 2026

Enabling Robots to Chart a Better Course

Researchers from Penn Engineering and MIT, including Vijay Kumar, have co-developed a new trajectory-planning system that enables an unpiloted aerial vehicle to react quickly to obstacles while staying on a smooth flight path that minimizes travel time. The open-source system could allow autonomous drones to streamline disaster recovery, parcel delivery, industrial inspection, and more.

Testing AI Against Public Health’s Existing Tools

A new randomized controlled trial has found that AI-powered chatbots can make vaccine-hesitant parents more likely to say they will immunize their children against HPV, but no more than standard written public health materials. “While chatbot conversations can move intentions immediately,” says Lyle Ungar, “their advantage disappeared when compared with well-designed public health materials and did not persist over time.”

Nadav Cornberg (Eve Security): Interrogating Agents Before They Act
6/11: The Road to Accountable AI | Kevin Werbach

Are Federal Courts Crowding Out State Court Law Making? An Insurance Law Case Study
6/10: 10th Annual Empirical Contracts Workshop | Tom Baker

Breaking Down the Biggest World Cup Ever
6/10: Wharton Moneyball | Shane Jensen

Machine-Learning Identified Suicide Risk and Emergency Department Inpatient Admission
6/10: General Hospital Psychiatry | Lyle Ungar

What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
6/9: arXiv | Aaron Roth

When AI Meets Insurance: Regulation, Accountability, Climate, and Affordability
6/9: Responsible AI & Analytics for Insurance Workshop | Kevin Werbach

The Ambition Premium and the Elon Musk Effect
6/8: Gad's Newsletter | Gad Allon

Large Language Model Chatbot Conversations vs Public Health Materials and Parental HPV Vaccination Intentions: A Randomized Clinical Trial
6/8: JAMA Network Open | Lyle Ungar

The Role of Standards in Enabling the AI Stack
6/8: Science and Technology Law Review | Christopher Yoo

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
6/6: CVPR 2026 | René Vidal

Learning to Strategically Acquire Resources in Competition
6/5: arXiv | Michael Kearns

Understanding Vaccine Hesitancy and Building Healthy Lives
6/4: Annenberg School for Communication | Sandra González-Bailón

Double Preconditioning (DoPr): Optimization for Test-Time Performance, Not Validation Loss
6/4: arXiv | Nikolai Matni

Trustworthy AI in Health: Foundation Models for Radiology, Cardiology and Autism Diagnosis
6/3: 12th CVPR Workshop on Medical Computer Vision | René Vidal

Formalizing the Binding Problem
6/2: arXiv | Konrad Kording

Limit Analysis of Graph Neural Networks With Wireless Conflict Graphs
6/2: arXiv | Alejandro Ribeiro

Everywhere Learning: Artificial Intelligence With Pointwise Constraints
6/1: arXiv | Alejandro Ribeiro

Belief Strength and the Attitudinal and Behavioural Correlates of Conspiracy Beliefs
5/31: British Journal of Social Psychology | Dolores Albarracín

Characterizing Metastable Faults and Failures
5/31: arXiv | Andreas Haeberlen

Stepsize Hedging: an Alternative Mechanism for Accelerating Gradient Descent
5/29: arXiv | Jason Altschuler

Multiagent Social Influence: Modeling Persuasion in Contested Social Networks
5/29: 2026 American Control Conference | Victor Preciado

Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why
5/25: arXiv | Chris Callison-Burch

Website

Get Involved

Past Events

107 Towne Building
220 South 33rd Street
Philadelphia, Pennsylvania 19104
warrenct@seas.upenn.edu

Manage your preferences | Opt Out using TrueRemove™
Got this as a forward? Sign up to receive our future emails.
View this email online.

Penn Engineering 107 Towne Building 220 South 33rd Street | Philadelphia, PA 19104 US

This email was sent to lhoot@seas.upenn.edu.
To continue receiving our emails, add us to your address book.