3 papers
cs.CV2026
Embedding-perturbed Exploration Preference Optimization for Flow Models
Sujie Hu, Chubin Chen, Jiashu Zhu +3
Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-based optimization framework…
cs.CV2026
Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning
Chubin Chen, Sujie Hu, Jiashu Zhu +8
Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, whil…
cs.CV2025
Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement
Yuqi Shen, Fengyang Xiao, Sujie Hu +5
Camouflaged Object Detection (COD) presents inherent challenges due to the subtle visual differences between targets and their backgrounds. While existing methods have made notable…