Understanding Search in Transformers
mechanistic interpretability of transformer networks trained on toy spatial tasks

Inverse Scaling
resistance to prompt injection might be an example of a task which exhibits inverse scaling in large transformer networks

Loss Symmetries
(coming soon)

CE-learn
Studying learning in the C. elegans nematode

RL-dreams
value function robustness for world-model RL by giving it weird dreams

BNBP
Training of Hodgkin-Huxley neural nets with SGD

ML for medical imaging
Segmentation of CT images using a U-Net architecture