Modern neural networks, with billions of parameters, are so overparameterized that they can "overfit" even random, ...

A paper co-authored by Prof. Alex Lew has been selected as one of four "Outstanding Papers" at this year's Conference on Language Modeling (COLM 2025), held in Montreal in October.

Researchers have developed an AI system that learns about the world via videos and demonstrates a notion of “surprise” when ...

A new study published in the Journal of Experimental Psychology: General suggests that personalization algorithms used by ...

A researcher from the University of Tokyo and a U.S.-based structural engineer developed a new computational form-finding ...

For years, quantum computers have been framed as the ultimate problem solvers, machines that would eventually crack any task that classical hardware could not touch. Now a new line of research is ...

In the GenAI era, program comprehension is not just another skill in the toolbox; it is the toolbox itself. It enables learners to move beyond passive acceptance of AI outputs, guiding them to ...

A new NURBS-based algorithm is revolutionizing gridshell design by enabling faster, smoother, and more flexible shape-finding ...

Recent hash table development raises questions about an optimal solution. Hash tables are one of the oldest and simplest data structures for storing elements and supporting deletions and queries.

Building on decades of effort, Lizhong Zhang, Member (2023–24) in the School of Natural Sciences; James Stone, Professor in ...

Some efforts to slash energy costs focus on using renewable sources, or on slimming down the AI models themselves. But ...

These science fiction masterpieces predicted aspects of the future with eerie uncanniness and left a lasting impression.