Vison-related research artifacts of WestAI, including image-only or vision-language models and datasets.
AI & ML interests
Large-scale multi-modal transferable learning of complex AI models
Recent Activity
Video research artifacts of WestAI.
Text research artifacts of WestAI.
Models of the paper "HyenaPixel: Global Image Context with Convolutions"
GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model
Audio research artifacts of WestAI.
3D research artifacts of WestAI.
Audio research artifacts of the WestAI and LAION collaboration.
OpenFlamingo, a family of autoregressive vision-language models ranging from 3B to 9B parameters.
Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference
Vison-related research artifacts of WestAI, including image-only or vision-language models and datasets.
Audio research artifacts of WestAI.
Video research artifacts of WestAI.
3D research artifacts of WestAI.
Text research artifacts of WestAI.
Audio research artifacts of the WestAI and LAION collaboration.
Models of the paper "HyenaPixel: Global Image Context with Convolutions"
OpenFlamingo, a family of autoregressive vision-language models ranging from 3B to 9B parameters.
GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model
Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference