jxzhangjhu/advflow

[NeurIPS2020] The official repository of "AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows".

Hi there, I am Jiaxin 👋!

🔭 I am a Staff Research Scientist at Intuit AI Research where my focus is Generative AI (large language models (LLMs), and diffusion models), and AI Robustness & Safety (uncertainty, reliability, and trustworthiness) with extensive applications to complex real-world tasks. Previously, I was a Research Staff in the Computer Science and Mathematics Division at Oak Ridge National Laboratory where my research aims at accelerating AI for Science on supercomputers, such as Summit and Frontier. I received my Ph.D. from the Johns Hopkins University with an emphasis on uncertainty quantification (UQ).

📫 You may find more information through my personal website and feel free to contact me via email at [email protected].

😄 Some recent publications in LLMs (full publication list in Google Scholar)

• [NeurIPS 2023] Jiaxin Zhang, Zhuohang Li, Kamalika Das, and Sricharan Kumar. Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision.
• [EMNLP 2023] Jiaxin Zhang, Zhuohang Li, Kamalika Das, Bradley Malin, and Sricharan Kumar. SAC$^3$: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency.