3 citations · 10 across the 7 of their papers we have counts for
8 papers
Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Ruofan Jin, Zaixi Zhang
Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations. However, current VLA tr…
Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity
Zaixi Zhang, Souradip Chakraborty, Amrit Singh Bedi +16
The rapid adoption of generative artificial intelligence (GenAI) in the biosciences is transforming biotechnology, medicine, and synthetic biology. Yet this advancement is intrinsi…
SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models
Jigang Fan, Zhenghong Zhou, Ruofan Jin +3
Proteins play crucial roles in almost all biological processes. The advancement of deep learning has greatly accelerated the development of protein foundation models, leading to si…
LabOS: The AI-XR Co-Scientist That Sees and Works With Humans
Le Cong, David Smerkous, Xiaotong Wang +30
Modern science advances fastest when thought meets action. LabOS represents the first AI co-scientist that unites computational reasoning with physical experimentation through mult…
Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins
Zaixi Zhang, Ruofan Jin, Le Cong +1
DNA language models have revolutionized our ability to understand and design DNA sequences--the fundamental language of life--with unprecedented precision, enabling transformative…
GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance
Zaixi Zhang, Zhenghong Zhou, Ruofan Jin +2
DNA, encoding genetic instructions for almost all living organisms, fuels groundbreaking advances in genomics and synthetic biology. Recently, DNA Foundation Models have achieved s…
PoseX: AI Defeats Physics Approaches on Protein-Ligand Cross Docking
Yize Jiang, Xinze Li, Yuanyuan Zhang +13
Existing protein-ligand docking studies typically focus on the self-docking scenario, which is less practical in real applications. Moreover, some studies involve heavy frameworks…
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
Ouxiang Li, Yanbin Hao, Zhicai Wang +4
Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MI…