Skip to content

Author

Xuan Ouyang

UNSW

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Test-Time Training with Next-Token Prediction

Test-Time Training with Next-Token Prediction (TTT-NTP), a drop-in fast-weight adaptation method for pretrained LLMs that instead supervises updates using the model's own next contextual hidden state, while preserving commonsense and knowledge performance.

Xuan Ouyang, Zefan Cai, Junjie Hu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.