7 papers
Left properness of Moore flows
Philippe Gaucher
We introduce the notion of a reparametrization category with cuts. For every such reparametrization category , we prove the tensor lemma, namely that the tensor product…
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
Xin Qiu, Yulu Gan, Conor F. Hayes +6
The paper shows that evolution strategies can successfully fine‑tune billion‑parameter large language models without backpropagation, outperforming reinforcement learning in stabil…
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…
TerraLingua: Emergence and Analysis of Open-endedness in LLM Ecologies
Giuseppe Paolo, Jamieson Warner, Hormoz Shahrzad +3
As autonomous agents increasingly operate in real-world digital ecosystems, understanding how they coordinate, form institutions, and accumulate shared culture becomes both a scien…
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…
Learning from the Past: How Previous Technological Transformations Can Guide AI Development
Risto Miikkulainen, Jerry Smith, Babak Hodjat
Artificial Intelligence (AI) is rapidly changing many areas of society. While this transformation has tremendous potential, there are several challenges as well. Using the history…