Multimodal Weekly #35: Vision Mamba

​​​In the 35th session of Multimodal Weekly, we welcome the researchers from Huazhong University of Science and Technology to share their latest work on efficient visual representation learning with bidirectional state space model.

​Professor Xinggang Wang, alongside his 2 Ph.D. students Lianghui Zhu and Bencheng Liao, will give a presentation about Vision Mamba - a new generic vision backbone with bidirectional Mamba blocks.

​Here are some resources:

• ​Paper

• ​Code

• ​HuggingFace

​​Multimodal Weekly is organized by Twelve Labs, a startup building multimodal foundation models for video understanding.

• ​Learn more about Twelve Labs here: https://twelvelabs.io/

• ​​Join our Multimodal Minds community: https://discord.gg/Sh6BRfakJa