← Search

Yingzi Ma

2 accepted papers

2025

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

ICLR 2025poster

Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy concerns in Vision Language Models (VLMs) remain underexplored. To address this, we introduce Facial Identity Unlearning…

2024

Dolphins: Multimodal Language Model for Driving

ECCV 2024poster

"The quest for fully autonomous vehicles (AVs) capable of navigating complex real-world scenarios with human-like understanding and responsiveness. In this paper, we introduce , a novel vision-language model architected to imbibe human-like abilities as a conversational driving assistant. is adept a…