activity
19952023
most citedCosmological Constraints from the SDSS Luminous Red Galaxies

1.4k citations · 3.9k across the 30 of their papers we have counts for

collaborators
Showing 2023Show all

5 papers · 1 filter

cs.CY202310 cited

Provably safe systems: the only path to controllable AGI

Max Tegmark, Steve Omohundro

We describe a path to humanity safely thriving with powerful Artificial General Intelligences (AGIs) by building them to provably satisfy human-specified requirements. We argue tha…

cs.NE20232 cited

Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability

Ziming Liu, Eric Gan, Max Tegmark

We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric spac…

cs.LG2023

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

Ziqian Zhong, Ziming Liu, Max Tegmark +1

Do neural networks, trained on well-understood algorithmic tasks, reliably rediscover known algorithms for solving those tasks? Several recent studies, on tasks ranging from group…

cs.LG2023

The Quantization Model of Neural Scaling

Eric J. Michaud, Ziming Liu, Uzay Girit +1

We propose the Quantization Model of neural scaling laws, explaining both the observed power law dropoff of loss with model and data size, and also the sudden emergence of new capa…

cs.LG202311 cited

PFGM++: Unlocking the Potential of Physics-Inspired Generative Models

Yilun Xu, Ziming Liu, Yonglong Tian +3

We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generati…