3 papers
cs.CV2026
Uni-Animator: Towards Unified Visual Colorization
Xinyuan Chen, Yao Xu, Shaowen Wang +2
We propose Uni-Animator, a novel Diffusion Transformer (DiT)-based framework for unified image and video sketch colorization. Existing sketch colorization methods struggle to unify…
cs.AI2025
Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs
Peidong Liu, Junjiang Lin, Shaowen Wang +5
Contextual Markov Decision Processes (CMDPs) offer a framework for sequential decision-making under external signals, but existing methods often fail to generalize in high-dimensio…
cs.SD2025
Self-Improvement for Audio Large Language Model using Unlabeled Speech
Shaowen Wang, Xinyuan Chen, Yao Xu
Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inev…