Lizhang Chen

activity

20232026

most citedCautious Optimizers: Improving Training with One Line of Code

3 citations · 3 across the 12 of their papers we have counts for

collaborators

Showing 2026Show all

4 papers · 1 filter

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 $π^{s i g n} = (1 + α) π^{+} - α π^{-}$ , where $α > 0$ , $π^{+}$ is the distribut…

cs.LG2026

Training-Free Looped Transformers

Lizhang Chen, Jonathan Li, Chen Liang +2

We introduce training-free looped transformers, in which a lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional…

cs.LG2026

$ϕ$ -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.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…

Signed Rectified Flow: Negativity-Controlled Generation

Training-Free Looped Transformers

ϕ-Balancing for Mixture-of-Experts Training

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

$ϕ$ -Balancing for Mixture-of-Experts Training