Publications (52)
New Generation Value Networks for Content Delivery
Stefano Iellamo, Guenter Klas, Kevin Smith
In this paper we paint a broad picture of the Internet content delivery market, by taking into consideration both economical and technical challenges that might drive the interacti…
Physion: Evaluating Physical Prediction from Vision in Humans and Machines
Daniel M. Bear, Elias Wang, Damian Mrowca +12
While current vision algorithms excel at many challenging tasks, it is unclear how well they understand the physical dynamics of real-world environments. Here we introduce Physion,…
What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors
Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei +2
Transfer learning is a standard technique to transfer knowledge from one domain to another. For applications in medical imaging, transfer from ImageNet has become the de-facto appr…
Efficient Self-Supervised Adaptation for Medical Image Analysis
Moein Sorkhei, Emir Konuk, Jingyu Guo +3
Self-supervised adaptation (SSA) improves foundation model transfer to medical domains but is computationally prohibitive. Although parameter efficient fine-tuning methods such as…
The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models
Robert Welch, Emir Konuk, Kevin Smith
Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reas…
SPEC CPU: The Next Generation
Mahesh Madhav, Allen Lee, Andres Mejia +33
The march toward developing relevant and robust CPU benchmarks continues with the introduction of SPEC CPU 2026, the next generation suite for measuring processor performance. This…