activity
20242026
collaborators

10 papers

stat.ML2026

Optimal control of the future via prospective learning with control

Yuxin Bai, Aranyak Acharyya, Ashwin De Silva +3

Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (RL). RL is mathematically distinct fro…

q-bio.NC2026

Compiling molecular ultrastructure into neural dynamics

Konrad P. Kording, Anton Arkhipov, Davy Deng +22

High-resolution brain imaging can now capture not just synapse locations but their molecular composition, with the cost of such mapping falling exponentially. Yet such ultrastructu…

cs.LG2025

AutoGMM: Automatic Gaussian Mixture Modeling in Python

Tingshan Liu, Thomas L. Athey, Benjamin D. Pedigo +1

The exponential growth of complex data demands fully automatic clustering. Gaussian mixture models (GMMs) provide uncertainty-aware grouping but often require expertise to specify…

cs.AI2025

Simple Lifelong Learning Machines

Jayanta Dey, Joshua T. Vogelstein, Hayden S. Helm +13

In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorith…

cs.NE2025

Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures

Siyu Yu, Zihan Qin, Tingshan Liu +4

The complete connectome of the Drosophila larva brain offers a unique opportunity to investigate whether biologically evolved circuits can support artificial intelligence. We conve…

cs.LG2025

Prospective Learning in Retrospect

Yuxin Bai, Cecelia Shuai, Ashwin De Silva +3

In most real-world applications of artificial intelligence, the distributions of the data and the goals of the learners tend to change over time. The Probably Approximately Correct…