7 papers
Efficient Pre-Training of LLMs through Truncated SVD Layers
Kaivan Kamali, Kajetan Schweighofer, Hormoz Shahrzad +3
The massive scaling of Large Language Models (LLMs) has made pretraining increasingly cost-prohibitive. While low-rank representation and orthonormal weight matrices could in princ…
Optimizing Chlorination in Water Distribution Systems via Surrogate-assisted Neuroevolution
Rivaaj Monsia, Daniel Young, Olivier Francon +1
Ensuring the microbiological safety of large, heterogeneous water distribution systems (WDS) typically requires managing appropriate levels of disinfectant residuals including chlo…
Solving a Million-Step LLM Task with Zero Errors
Elliot Meyerson, Giuseppe Paolo, Roberto Dailey +6
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by h…
Leveraging Evolutionary Surrogate-Assisted Prescription in Multi-Objective Chlorination Control Systems
Rivaaj Monsia, Olivier Francon, Daniel Young +1
This short, written report introduces the idea of Evolutionary Surrogate-Assisted Prescription (ESP) and presents preliminary results on its potential use in training real-world ag…
Optimizing the Design of an Artificial Pancreas to Improve Diabetes Management
Ashok Khanna, Olivier Francon, Risto Miikkulainen
Diabetes, a chronic condition that impairs how the body turns food into energy, i.e. blood glucose, affects 38 million people in the US alone. The standard treatment is to suppleme…
Discovering Effective Policies for Land-Use Planning with Neuroevolution
Daniel Young, Olivier Francon, Elliot Meyerson +5
How areas of land are allocated for different uses, such as forests, urban areas, and agriculture, has a large effect on the terrestrial carbon balance, and therefore climate chang…