https://scholar.google.com/citations?view_op=list_works&hl=en&hl=en&user=eKs-ZGQAAAAJ
https://www.linkedin.com/in/hengyi-wang-86605b175/
Hengyi Wang (恒屹 王) is a 4th-year Ph.D. student at https://www.rutgers.edu/. His research is also supported by credits from https://cloud.google.com/edu/researchers?hl=en. Previously, he graduated with a B.S. in computer science from Turing Honor Class, https://english.pku.edu.cn/. He is fortunate to be advised by http://www.wanghao.in/, and has had the opportunity to collaborate with https://www.microsoft.com/en-us/research/people/akshayn/, https://www.microsoft.com/en-us/research/people/taganu/, https://www.amazon.science/author/bernie-wang, Prof. Jian Tang, Prof. Hongyu Guo, and https://csbphd.mit.edu/faculty/connor-w-coley.
His research is at the intersection of statistical machine learning and AI safety. Currently, he works on Bayesian deep learning and its real-world applications, such as multimodal large language models (MLLMs) and information retrieval. The goal of his research is to build trustworthy and safe AI systems, with a special focus on interpretability and alignment for the benefit of humanity.
(* indicates equal contribution)
Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models [paper][code][poster] Hengyi Wang*, Shiwei Tan*, Hao Wang 41th International Conference on Machine Learning (ICML 2024)
Variational Language Concepts for Interpreting Pretrained Language Models
Hengyi Wang, Shiwei Tan, Zhiqing Hong, Desheng Zhang, Hao Wang [code][paper]
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)
Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models [project][paper][code][leaderboard][slides] Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang Submitted to a Top ML Conference, Currently Under Review
Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction [paper][code][spotlight] Hangrui Bi*, Hengyi Wang*, Chence Shi, Connor Coley, Jian Tang, Hongyu Guo 38th International Conference on Machine Learning (ICML 2021)