TaiMing Lu

I'm an undergraduate student at Johns Hopkins University.

At Hopkins, I work with Prof. Daniel Khashabi, Phillip Koehn, and Alan Yuille.

I research Generative Foundation Models (e.g., LLMs, VLMs, Diffusion Models) and explore their possibilities. My interest spans Machine Learning, Natural Language Processing, and Computer Vision.

Google Scholar  /  Twitter  /  Github  |  tlu37@jhu.edu

profile photo

@EMNLP 2024

News
  • Selected Michael J. Muuss Undergraduate Research Award at JHU 🎇.
  • Genex accepted by ICLR 🥳.
  • Selected Finalist for CRA's Outstanding Undergraduate Researcher Award 🫡.
  • Genex (Generative World Explorer) is on arXiv! View our demo on project website or YouTube !
  • Poster presentation at EMNLP 🥸.

Publications
GenEx: Generating an Explorable World
Taiming Lu, Tianmin Shu, Junfei Xiao, Luoxin Ye, Jiahao Wang, Cheng Peng, Chen Wei, Daniel Khashabi, Rama Chellappa, Alan Yuille, Jieneng Chen
ICLR 2025    Paper | Project | Video | Poster
Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell
Taiming Lu, Muhan Gao, Kuai Yu, Adam Byerly, Daniel Khashabi
EMNLP 2024 (Findings)    Paper | Code | Poster
Learn and Unlearn in Multilingual LLMs
Taiming Lu, Philipp Koehn
Preprint    Paper | Code | Data
It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF
Taiming Lu, Lingfeng Shen, Xinyu Yang, Weiting Tan, Beidi Chen, Huaxiu Yao
ICML 2024 Workshop on Foundation Models in the Wild    Paper | Code

Others