2 papers
cs.LG2026
nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding
Boyang Li, Yulin Wu, Sizhe Xu +5
Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing appro…
cs.CV2025
InfoScale: Unleashing Training-free Variable-scaled Image Generation via Effective Utilization of Information
Guohui Zhang, Jiangtong Tan, Linjiang Huang +4
Diffusion models (DMs) have become dominant in visual generation but suffer performance drop when tested on resolutions that differ from the training scale, whether lower or higher…