🔄 In a Training Loop

Benhao Huang PRO

HuskyDoge

IFM

·

https://huskydoge.github.io

AI & ML interests

CS, AI interpretability, Software

Recent Activity

upvoted a paper 5 days ago

Cache Engineering for Agents

upvoted a paper 6 days ago

Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation

authored a paper 9 days ago

Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design

View all activity

Organizations

HuskyDoge 's papers 9

arxiv:2610.23036

arxiv:2610.06833

arxiv:2605.21488

arxiv:2601.01075

arxiv:2511.09057

arxiv:2506.21876

arxiv:2406.07275

arxiv:2402.02095

arxiv:2401.16318