Cite
Notes
Only stored in your browser.
Attribution
Code as Agent Harness
arXiv 2026
dLLM: Simple Diffusion Language Modeling
VLMs Can Aggregate Scattered Training Patches
arXiv 2025
Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
arXiv 2024
from 4 papers
Hanghang Tong
Zhanhui Zhou
Bingxuan Li
Chao Yang
Chaochao Lu
Cheng Qian
Chenyuan Yang
Dawn Song
professor
Dongqi Fu
Dorothy Sun