7 papers
Intelligence from Learnable Novelty
Yanbo Zhang, Michael Levin
Intelligence appears under different names in different fields: as data compression in statistics and machine learning, as universal computation in dynamical systems, and as adapti…
Diffusion Models are Evolutionary Algorithms
Yanbo Zhang, Benedikt Hartl, Hananel Hazan +1
In a convergence of machine learning and biology, we reveal that diffusion models are evolutionary algorithms. By considering evolution as a denoising process and reversed evolutio…
A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
Hananel Hazan, Yanbo Zhang, Benedikt Hartl +1
How many of a neural network's parameters actually encode task-specific information? We investigate this question with LottaLoRA, a training paradigm in which every backbone weight…
Equilibrium flow: From Snapshots to Dynamics
Yanbo Zhang, Michael Levin
Scientific data, from cellular snapshots in biology to celestial distributions in cosmology, often consists of static patterns from underlying dynamical systems. These snapshots, w…
ZapGPT: Free-form Language Prompting for Simulated Cellular Control
Nam H. Le, Patrick Erickson, Yanbo Zhang +2
Human language is one of the most expressive tools for conveying intent, yet most artificial or biological systems lack mechanisms to interpret or respond meaningfully to it. Bridg…
Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery
Yanbo Zhang, Sumeer A. Khan, Adnan Mahmud +10
With recent Nobel Prizes recognising AI contributions to science, Large Language Models (LLMs) are transforming scientific research by enhancing productivity and reshaping the scie…