https://scholar.google.com/citations?view_op=list_works&hl=en&hl=en&user=eKs-ZGQAAAAJ

https://github.com/AaronWhy

https://www.linkedin.com/in/hengyi-wang-86605b175/

https://x.com/HENGYIWANG24776

Bio

I am Hengyi Wang (恒屹 王), a 4th-year Ph.D. candidate at https://www.rutgers.edu/. My research is also supported by credits from https://cloud.google.com/edu/researchers?hl=en. Previously, I graduated with a B.S. in computer science from Turing Honor Class, https://english.pku.edu.cn/. I am fortunate to be advised by http://www.wanghao.in/, and have had the opportunity to collaborate with https://www.microsoft.com/en-us/research/people/akshayn/, https://www.microsoft.com/en-us/research/people/taganu/, and https://mila.quebec/en/directory/jian-tang.

Research Interests

My research focuses on the intersection of probabilistic machine learning and AI safety. I am currently working on interpretability and evaluation in areas such as multimodal large language models and personalized recommendation systems. The aim of my research is to develop understandable and controllable Artificial General Intelligence systems, with a particular emphasis on interpretability and alignment for the benefit of humanity.

News

• (01/22/2025) Multimodal Needle in a Haystack (MMNeedle) was accepted at NAACL 2025 Main (Oral Presentation). See you in Albuquerque！
• (09/20/2024) Our paper “Variational Language Concepts for Interpreting Foundation Language Models” was accepted at EMNLP 2024 Findings. See you in Miami!
• (06/17/2024) We released the paper, code, and data for Multimodal Needle in a Haystack (MMNeedle) benchmark. Check our **project page** and feel free to use our benchmark！
• (05/01/2024) Our paper “Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models” was accepted at ICML 2024.

Selected Publications

(* indicates equal contribution)

• Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics （NAACL 2025, Oral Presentation*）*

  

  [project][paper][code][leaderboard][slides]

• Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models Hengyi Wang*, Shiwei Tan*, Hao Wang 41th International Conference on Machine Learning (ICML 2024)

  

  [paper][code][poster]

• Variational Language Concepts for Interpreting Foundation Language Models

  Hengyi Wang, Shiwei Tan, Zhiqing Hong, Desheng Zhang, Hao Wang

  The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)

  

  [[paper]](http://arxiv.org/abs/2410.03964)[code][poster][talk][slides]

• Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction Hangrui Bi*, Hengyi Wang*, Chence Shi, Connor Coley, Jian Tang, Hongyu Guo 38th International Conference on Machine Learning (ICML 2021)

  

  [paper][code][spotlight][slides]