Spaces:

---

lmms-lab

/

Multimodal-SAE

like 8

Running on Zero

Hi, I am applying for Zero GPU support for the demo for our paper Large Multi-modal Models Can Interpret Features in Large Multi-modal Models.

Here are the information and links for our paper:
🔍 ArXiv Paper | 🏠 LMMs-Lab Homepage | 🤗 Huggingface Collections | GitHub Repo | HF Paper Page

I have built and successfully run the demo on my local server, but is hoping to be granted Zero GPU for further debugging on huggingface space. A temporary link for demonstration can be found here

Thank you!

@misc
	{zhang2024largemultimodalmodelsinterpret,
      title={Large Multi-modal Models Can Interpret Features in Large Multi-modal Models},
      author={Kaichen Zhang and Yifei Shen and Bo Li and Ziwei Liu},
      year={2024},
      eprint={2411.14982},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2411.14982},
}