3 papers
cs.CV2026
Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution
Xingfu Yi, Xiaoxue Yu
Recent real-world image super-resolution (SR) methods often adapt text-to-image (T2I) backbones with ControlNet-style branches or spatial conditioning tokens, which increases memor…
cs.CV2026
In-Token Learning for High-Fidelity Image Restoration via Diffusion Transformers
Xingfu Yi, Xiaoxue Yu
We present In-Token Learning, an image restoration framework that adapts a pretrained diffusion transformer using conditional rectified flow matching. Clean targets paired with deg…
cs.NI2024
Snake Learning: A Communication- and Computation-Efficient Distributed Learning Framework for 6G
Xiaoxue Yu, Xingfu Yi, Rongpeng Li +4
In the evolution towards 6G, integrating Artificial Intelligence (AI) with advanced network infrastructure emerges as a pivotal strategy for enhancing network intelligence and reso…