Long-term AI Safety Research @ Cornell

university

https://lionllevine.github.io

AI & ML interests

None defined yet.

Recent Activity

Suvadip2776 updated a Space 9 days ago

Suvadip2776 published a Space 10 days ago

invi-bhagyesh updated a collection about 1 month ago

View all activity

updated a Space 9 days ago

NYCC

NYCC Proxy Agent for character training

published a Space 10 days ago

NYCC

NYCC Proxy Agent for character training

updated 2 collections about 1 month ago

midtraining

https://arxiv.org/abs/2605.02087 • 2 items • Updated 9 days ago

olmo

11 items • Updated Aug 29

updated a Space about 1 month ago

ValueArena

Run model ranking pipeline and publish results to ValueArena

published a Space about 1 month ago

ValueArena

Run model ranking pipeline and publish results to ValueArena

authored a paper 10 months ago

TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models

Paper • 2511.15807 • Published Nov 19, 2025