3 papers
cs.LG2026
Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
Yixian Xu, Yuanrui Zhang, Shengjie Luo +2
Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, current RL algorithms for diffu…
cs.CV2026
Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning
Enhan Zhao, Wei Wu, Yuanrui Zhang +2
Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs). Existing approaches largely rely on large-scale, statically curated datasets, where a…
cs.CV2026
Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models
Jiayi Xu, Zhang Zhang, Yuanrui Zhang +4
In this paper, we introduce \emph{Luminark}, a training-free and probabilistically-certified watermarking method for general vision generative models. Our approach is built upon a…