Toronto

Yangjun Ruan

Advanced
@ryoungj

Ph.D. student @ UofT & Vector Previously undergrad @ ZJU

www.cs.toronto.edu/~yjruan/

ToolEmu. [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use

211

BoLT. Code for "Reasoning to Learn from Latent Thoughts"

133

ObsScaling. [NeurIPS'24 Spotlight] Observational Scaling Laws

60

optdom. [ICLR'22] Self-supervised learning optimally robust representations for domain shift.

25

mcbits. [ICML'21 Oral] Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

14

ZO-L2L. [ICLR'20] Learning to Learn by Zeroth-Order Oracle

14
6
Apply