Suggestions
Haohan Wang
Assistant Professor at University of Illinois at Urbana-Champaign specializing in trustworthy machine learning and computational biology
Haohan Wang is an assistant professor in the School of Information Sciences at the University of Illinois Urbana-Champaign.12 He joined the faculty in August 2022 after completing his PhD in computer science at Carnegie Mellon University.34
Research Focus
Wang's research primarily focuses on two main areas:
-
Trustworthy Machine Learning: He develops methods to make machine learning algorithms more reliable and robust, particularly for applications in computational biology and healthcare.25
-
Computational Biology: Wang works on understanding the genetic basis of complex human disorders, with a particular emphasis on Alzheimer's disease.25
Academic Background
- PhD: Computer Science, Carnegie Mellon University (2015-2021)34
- MS: Carnegie Mellon University (2012-2014)4
- BS: Beijing University of Post and Telecommunication (2008-2012)4
Notable Achievements
- Recognized as one of the top 50 AI+X rising young scholars by Baidu Inc. in 20222
- Named as part of the "Next Generation: Rising Stars in Biomedicine" by the Broad Institute of MIT and Harvard in 20191
Professional Activities
Wang is an organizer of the Trustworthy Machine Learning Initiative.1 He has given numerous talks and tutorials on trustworthy machine learning and its applications in computational biology at various conferences and institutions.2
Research Goals
Wang aims to develop machine learning tools that can be reliably used by physicians and biologists without requiring extensive machine learning expertise.5 His ultimate goal is to create trustworthy algorithms that can consistently provide accurate and reproducible results in understanding and treating complex disorders like Alzheimer's disease.5
Highlights
🌟 Exciting Update in AI Safety Research! 🌟
We're thrilled to announce the release of our comprehensive survey, 📕 JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models 📕 .
This work explores the rapidly advancing field of jailbreaking AI models, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs).
🔍 Why It Matters: Jailbreaking AI models is a critical topic as it unveils potential vulnerabilities and informs the development of robust defense mechanisms. However, keeping pace with the latest advancements and strategies can be daunting. Our survey provides a structured framework, making it accessible to both newcomers and seasoned researchers.
🛠️ What We Offer:
- A detailed categorization of jailbreak strategies.
- Analysis of emerging defense mechanisms.
- Interactive demos on our dedicated website to illustrate concepts in real-time.
📈 Get Involved: Our goal is to foster a community around the secure and ethical development of AI technologies. We invite researchers, practitioners, and enthusiasts to engage with our work:
Explore the survey and demos: https://lnkd.in/gT6i_7fa Join the conversation and collaborate on our GitHub: https://lnkd.in/gzbwTneV Read our Manuscript: https://lnkd.in/g9vC4s8e
Your insights and contributions are invaluable as we navigate the complexities of AI security together. Let's shape the future of AI in a secure and responsible manner!
#AI #MachineLearning #Cybersecurity #ArtificialIntelligence #Innovation #ResearchCommunity
Paving a New Era of AI-Driven Science: Benchmark and Agent Solutions to Automate End-to-End Scientific Discovery
🔭 Imagine AI agents working as scientists, handling every step of research from picking datasets to creating hypotheses, just like bioinformaticians do. These agents change how AI is used, taking on detailed analyses and result interpretation—tasks usually done by human experts.
🚀 Building upon this innovative concept, we are excited to unveil GenoTEX, a transformative benchmark for automating scientific discovery processes in genomics, focusing on gene expression data. GenoTEX is designed not merely as a dataset but as a comprehensive suite to evaluate and enhance AI-driven methods in genomics data analysis. By establishing this benchmark, we aim to pioneer advancements where our AI agents—our GenoAgents—emulate bioinformaticians to perform comprehensive, end-to-end scientific investigations.
🧬 About GenoTEX: GenoTEX covers the full cycle of scientific research, from selecting and preprocessing data to performing detailed statistical analysis. The benchmark follows a standardized pipeline, checked by expert bioinformaticians, to ensure the AI-generated results are accurate and reliable. Importantly, the datasets in GenoTEX are manually curated, involving 181 relevant datasets with 163 successfully preprocessed, showcasing over 71,669 lines of manually written code for analysis. This benchmark provides extensive annotated code and results for 1,146 gene identification problems—both unconditional (82) and conditional (1,064)—which serve as a robust foundation for developing and evaluating AI methods in genomics.
🤖 Introducing GenoAgents: Alongside GenoTEX, we introduce GenoAgents, a suite of AI-driven agents crafted to tackle the nuanced tasks traditionally reserved for human experts. These agents are designed with capabilities that include context-aware planning, iterative correction, and domain expertise integration, simulating a collaborative environment similar to a team of human researchers. Our evaluation shows that GenoAgents can automate the process of gene expression data analysis with good overall accuracy, presenting a promising method for future research in genomics.
Our work highlight the potential of LLM-based approaches to significantly reduce the labor-intensive aspects of gene data analysis. We invite the scientific and tech community to explore GenoTEX and participate in evolving this benchmark. Your insights and contributions are crucial as we strive to refine AI applications in real-world scientific contexts.
Benchmark arXiv link: https://lnkd.in/gkZiNehN previous workshop version: https://lnkd.in/gXzXcEX6 GitHub link: https://lnkd.in/gnrMni3u
