Hi there! 👋 Thanks for stopping by.
📎 PixelProse-16M: A large-scale dataset of 16 million dense image-caption pairs. [ 🤗 Dataset ].
📎 Zebra-CoT: A dataset for interleaved vision language reasoning. [ 🤗 Dataset ]
PyTorch Implementation of Image Generation with a Sphere Encoder
PyTorch Implementation of Zero-Shot Vision Encoder Grafting via LLM Surrogates [ICCV'25]
PyTorch Implementation of Compact Generalized Non-local Network [NIPS'18]