6 papers
Maglev: Sliding Recurrent Memory
Bo Liu, Qiang Liu
We introduce \ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizable during training. \ours{}…
Cautious Optimizers: Improving Training with One Line of Code
Kaizhao Liang, Lizhang Chen, Bo Liu +1
AdamW has been the default optimizer for transformer pretraining. For many years, our community searched for faster and more stable optimizers with only constrained positive outcom…
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…
Muon Optimizes Under Spectral Norm Constraints
Lizhang Chen, Jonathan Li, Qiang Liu
The pursuit of faster optimization algorithms remains an active and important research direction in deep learning. Recently, the Muon optimizer [JJB+24] has demonstrated promising…
AMO Sampler: Enhancing Text Rendering with Overshooting
Xixi Hu, Keyang Xu, Bo Liu +2
Achieving precise alignment between textual instructions and generated images in text-to-image generation is a significant challenge, particularly in rendering written text within…
Improving Adaptive Moment Optimization via Preconditioner Diagonalization
Son Nguyen, Bo Liu, Lizhang Chen +1
Modern adaptive optimization methods, such as Adam and its variants, have emerged as the most widely used tools in deep learning over recent years. These algorithms offer automatic…