Zhuang Liu
2 papers · Latest:
Computer Vision
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
VisionFoundry uses an LLM-driven pipeline to generate synthetic image data, significantly improving VLMs' visual perception skills.
2604.09531
Computer VisionDensely Connected Convolutional Networks
DenseNet introduces a convolutional network architecture that connects each layer to every other layer, improving accuracy, efficiency, and feature reuse.
1608.06993
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.