collaborators

6 papers

cs.CV2026

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation

Xiaoxiao Ma, Jiachen Lei, Tianfei Ren +6

Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging d…

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…

cs.CV2025

FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment

Hang Xu, Jie Huang, Linjiang Huang +3

Domain Adaptation(DA) for dense prediction tasks is an important topic, which enhances the dense prediction model's performance when tested on its unseen domain. Recently, with the…

cs.CV2025

Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution

Hang Xu, Wei Yu, Jiangtong Tan +2

Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous meth…

cs.CV2025

FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component Analysis

Jiangtong Tan, Hu Yu, Jie Huang +2

Long video generation involves generating extended videos using models trained on short videos, suffering from distribution shifts due to varying frame counts. It necessitates the…

stat.ML2025

AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse

Zichao Yu, Zhen Zou, Guojiang Shao +6

Diffusion models have demonstrated remarkable success in generative tasks, yet their iterative denoising process results in slow inference, limiting their practicality. While exist…