6 papers
Dion3: Full-Stack Orthogonal Updates
Noah Amsel, Jack Zhang, Kwangjun Ahn +5
The Muon optimizer incurs a significant overhead cost due to its cubic-time Newton-Schulz orthogonalization step. When weights are sharded, communication overhead compounds this co…
Next-Latent Prediction Transformers Learn Compact World Models
Jayden Teoh, Manan Tomar, Kwangjun Ahn +7
Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent i…
Dion2: A Simple Method to Shrink Matrix in Muon
Kwangjun Ahn, Noah Amsel, John Langford
The Muon optimizer enjoys strong empirical performance and theoretical grounding. However, the super-linear cost of its orthonormalization step introduces increasing overhead with…
The Belief State Transformer
Edward S. Hu, Kwangjun Ahn, Qinghua Liu +9
We introduce the "Belief State Transformer", a next-token predictor that takes both a prefix and suffix as inputs, with a novel objective of predicting both the next token for the…
Dion: Distributed Orthonormalized Updates
Kwangjun Ahn, Byron Xu, Natalie Abreu +5
Orthonormalized updates accelerate training, improve stability, and enable robust hyperparameter transfer, but existing methods like Muon rely on dense matrix operations that clash…
Efficient Joint Prediction of Multiple Future Tokens
Kwangjun Ahn, Alex Lamb, John Langford
In this short report, we introduce joint multi-token prediction (JTP), a lightweight modification of standard next-token prediction designed to enrich hidden state representations…