Kaishen Wang

Select the Key, Then Generate the Rest: Improving Multi-Modal Learning with Limited Data Budget

FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks

DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models

Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models