Lang Gao's picture

Lang Gao

LangGao

·

https://heartyhaven.github.io/

AI & ML interests

Mechanistic Interpretability of AI

Recent Activity

updated a dataset 12 days ago

LangGao/CRH_Data

upvoted a paper about 1 month ago

The Cylindrical Representation Hypothesis for Language Model Steering

new activity about 1 month ago

LangGao/CRH_Data:Add dataset card, link to paper and GitHub repository

View all activity

Organizations

upvoted a paper about 1 month ago

The Cylindrical Representation Hypothesis for Language Model Steering

Paper • 2605.01844 • Published May 3 • 2

upvoted a paper 7 months ago

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

Paper • 2511.09057 • Published Nov 12, 2025 • 82

upvoted a paper 11 months ago

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs

Paper • 2505.15524 • Published May 21, 2025 • 8