← Search

Kaiyuan Cui

2 accepted papers

2026

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models

ICLR 2026poster

Vision–language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integration expands the attack surface by exposing the model to image-based jailbreaks crafted to induce harmful responses. E…

Cited by 0SourcecodeScholar
2025

Sampling from Binary Quadratic Distributions via Stochastic Localization

ICML 2025poster

Sampling from binary quadratic distributions (BQDs) is a fundamental but challenging problem in discrete optimization and probabilistic inference. Previous work established theoretical guarantees for stochastic localization (SL) in continuous domains, where MCMC methods efficiently estimate the requ…