الباحثون

Guiguang Ding

المنشورات 2

نسخة أولية وصول مفتوح

What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle

Peilin Wang, Feng Shiyang, Hongfu Gao وآخرون · 2026

Recursive computation repeatedly compresses or reuses intermediate states, creating a simple tension: information that must remain useful across longer recursive paths is also exposed to more opportunities for loss before reaching the final prediction. Existing reconstruction or local-prediction objectives provide trac …

نسخة أولية وصول مفتوح

RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance

Yiming Liu, Ben Wan, Tongxuan Liu وآخرون · 2026

Diffusion models enable high-quality visual generation, but iterative denoising remains computationally expensive, especially under classifier-free guidance (CFG), which requires both conditional and unconditional evaluations. Training-free caching reduces this cost by reuse of previously computed features or predictio …

المؤلفون المشاركون