الباحثون

Shiqi Huang

المنشورات 2

نسخة أولية وصول مفتوح

Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion

Chong Wang, Zixuan Fu, Shiqi Huang وآخرون · 2026

Pixel-space diffusion Transformers (DiTs) directly operate on high-dimensional visual data, yet their hidden representations typically undergo uniform refinement across depth. Natural images, however, are inherently organized at different levels of granularity. Global structure can often be represented compactly, where …

نسخة أولية وصول مفتوح

Copy the Same, Distill the Difference: Initializing Linear Vision Transformers

Huaiyuan Qin, Muli Yang, Gabriel James Goenawan وآخرون · 2026

Linear Vision Transformers (ViTs) are designed to replace the attention in Softmax ViTs with the linear-complexity attention operator for more efficient token routing, but they require from-scratch pre-training and typically underperform the original Softmax version. How to initialize linear ViTs both efficiently and e …

المؤلفون المشاركون