Shiyuan Guo — accepted AI-conference papers

2026

All Code, No Thought: Language Models Struggle to Reason in Ciphered Language

Shiyuan Guo, Henry Sleight, Fabien Roger

ICLR 2026poster

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT monitoring through *ciphered reasoning*: reasoning hidden in e…

Cited by 0 Source ↗code ↗Scholar ↗

2021

TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models

Zhuohan Li, Siyuan Zhuang, Shiyuan Guo, Danyang Zhuo, Hao Zhang, Dawn Song +1

ICML 2021spotlight

Model parallelism has become a necessity for training modern large-scale deep language models. In this work, we identify a new and orthogonal dimension from existing model parallel approaches: it is possible to perform pipeline parallelism within a single training sequence for Transformer-based lang…

Cited by 128 Source ↗PDF ↗code ↗Scholar ↗