Picture for Weili Zeng

Weili Zeng

Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting

Add code
Apr 22, 2024
Viaarxiv icon

Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Add code
Jul 03, 2023
Viaarxiv icon

How to Construct Energy for Images? Denoising Autoencoder Can Be Energy Based Model

Add code
Mar 05, 2023
Viaarxiv icon