Baiyu Su

collaborators

3 papers

cs.LG2026

Signed Rectified Flow: Negativity-Controlled Generation

Runlong Liao, Baiyu Su, Lizhang Chen +1

We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $I ¨ ^{s i g n} = (1 + I^\pm) I ¨ ^{+} - I^\pm I ¨ ^{-}$ , where $I^\pm > 0$ , $I ¨ ^{+}$ is the di…

cs.LG2026

Momentum Guidance: Plug-and-Play Guidance for Flow Models

Runlong Liao, Jian Yu, Baiyu Su +3

Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used in their vanilla conditional form: in…

cs.LG2026

Cautious Weight Decay

Lizhang Chen, Jonathan Li, Kaizhao Liang +6

We introduce Cautious Weight Decay (CWD), a one-line, optimizer-agnostic modification that applies weight decay only to parameter coordinates whose signs align with the optimizer u…