top of page
TURNINGPOINT AI.
Home
Publications
People
Join Us
More
Use tab to navigate through the menu items.
Publications
MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?
Xirui Li*, Hengguang Zhou*, Ruochen Wang, Tianyi Zhou, Minhao Cheng, Cho-Jui Hsieh
Under Review
MLLM Safety
Oversensitivity
Large Language Models are Interpretable Learners
Ruochen Wang, Si Si, Felix Yu, Dorothea Wiesmann, Cho-Jui Hsieh, Inderjit Dhillon
Google
Neuro-Symbolic Program
MLLM
Prompt Optimization
Benchmark
Interpretability
The Crystal Ball Hypothesis in Diffusion Models: Anticipating Object Positions from Initial Noise
Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Boqing Gong, Cho-Jui Hsieh, Minhao Cheng
Stable Diffusion
Controllable Generation
Detection
Bias
Dataset
DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, Cho-Jui Hsieh
Safety
Trustworthy AI
Jailbreak
One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
Ruochen Wang*, Sohyun An*, Minhao Cheng, Tianyi Zhou, Sung Ju Hwang, Cho-Jui Hsieh
ICML2024
Mixture-of-Experts
Prompt Optimization
MuLan: Multimodal-LLM Agent for Progressive Multi-object Diffusion
Sen Li, Ruochen Wang, Cho-Jui Hsieh, Minhao Cheng, Tianyi Zhou
Stable Diffusion
Controllable Generation
Interactive Editing
Understanding the Impact of Negative Prompts: When
and How Do They Take Effect?
Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Minhao Cheng, Boqing Gong, Cho-Jui Hsieh
Stable Diffusion
Controllable Generation
Inpainting
Image Editing
On Discrete Prompt Optimization for Diffusion Models
Ruochen Wang, Ting Liu, Cho-Jui Hsieh, Boqing Gong
ICML2024
Google
Deepmind
Stable Diffusion
Multimodal Alignment
Prompt Optimization
bottom of page