Changlin Li
2 papers · Latest:
Computer Vision
Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions
This paper introduces a framework for online video understanding that provides transparent decisions and precisely times responses to visual evidence.
2604.18459
Human-Computer InteractionReVis: Towards Reusable Image-Based Visualizations with MLLMs
ReVis is a human-AI system that uses MLLMs and a DSL to parse and reproduce image-based visualizations, enabling flexible reuse and customization.
2604.15781
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.