7 papers
Vidu S1: A Real-Time Interactive Video Generation Model
Jintao Zhang, Kai Jiang, Jintao Chen +24
We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment throug…
SageBwd: A Trainable Low-bit Attention
Jintao Zhang, Marco Chen, Haoxu Wang +5
Low-bit attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorly understood. In pri…
Delving into Muon and Beyond: Deep Analysis and Extensions
Xianbiao Qi, Marco Chen, Jiaquan Ye +2
The Muon optimizer has recently attracted considerable attention for its strong empirical performance and use of orthogonalized updates on matrix-shaped parameters, yet its underly…
SimpleGPT: Improving GPT via A Simple Normalization Strategy
Marco Chen, Xianbiao Qi, Yelin He +2
In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the He…
Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation
Feng Lin, Marco Chen, Haokui Zhang +3
This paper investigates the role of attention heads in CLIP's image encoder. Building on interpretability studies, we conduct an exhaustive analysis and find that certain heads, di…
DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
Xianbiao Qi, Marco Chen, Wenjie Xiao +4
Transformers have become the de facto backbone of modern deep learning, yet their training typically demands an advanced optimizer with adaptive learning rate like AdamW, rather th…