Qing Lian

Disentangled Generative Causal Representation Learning

2021

This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method. Unlike existing disentanglement methods that enforce independence of the latent variables, we consider the general case where the underlying factors of interests can be …

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance

2024 · arXiv (Cornell University)

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such attacks. Compared to …