Runlong Liao

collaborators

4 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

$I ¨ $ -Balancing for Mixture-of-Experts Training

Lizhang Chen, Jonathan Li, Qi Wang +5

Mixture-of-Experts (MoE) models rely on balanced expert utilization to fully realize their scalability. However, existing load-balancing methods are largely heuristic and operate o…

cs.LG2025

Improving Rectified Flow with Boundary Conditions

Xixi Hu, Runlong Liao, Keyang Xu +5

Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the v…

Signed Rectified Flow: Negativity-Controlled Generation

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

I¨-Balancing for Mixture-of-Experts Training

Improving Rectified Flow with Boundary Conditions

$I ¨ $ -Balancing for Mixture-of-Experts Training