5 papers
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
Renye Yan, Jikang Cheng, Shikun Sun +7
Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignment through explicit rewards.…
Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization
Yixiao Chen, Shikun Sun, Jianshu Li +3
Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial. Existing generator-based attacks…
V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos
Qixin Wang, Songtao Zhou, Zeyu Jin +3
Automatic video commentary systems are widely used on multimedia social media platforms to extract factual information about video content. However, current systems may overlook es…
Minimal Impact ControlNet: Advancing Multi-ControlNet Integration
Shikun Sun, Min Zhou, Zixuan Wang +7
With the advancement of diffusion models, there is a growing demand for high-quality, controllable image generation, particularly through methods that utilize one or multiple contr…
Skinned Motion Retargeting with Dense Geometric Interaction Perception
Zijie Ye, Jia-Wei Liu, Jia Jia +2
Capturing and maintaining geometric interactions among different body parts is crucial for successful motion retargeting in skinned characters. Existing approaches often overlook b…