Jiayu (Mila) Wang

Contact: milawang [at] cs [dot] wisc [dot] edu

I am Jiayu (pronounciation: “Jee-ah-yü Wahng”), a PhD student in Computer Sciences at UW-Madison. I am fortunate to be advised by Prof. Aws Albarghouthi and Prof. Fred Sala.

I am passionate about building efficient and intelligent foundation models. My recent works focus on:

  • Data- and compute-efficient Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) (e.g., LLM routing)
  • Logical and mathematical reasoning for LLMs and VLMs (e.g., grammar-aligned decoding, spatial reasoning)

I’m always happy to discuss research, answer questions, or just chat! Feel free to reach out through my socials (see RHS →).

news

Dec 5, 2024 I’ll be attending NeurIPS 2024 in Vancouver from December 9-14! I’m excited to present two papers:
  • SpatialEval: We took a fresh look at how language models and vision-language models handle spatial reasoning. The twist? We tested them on our new benchmark SpatialEval across TQA, VQA, and VTQA. Found some pretty surprising results!
  • GAD: Ever wondered if constrained decoding changes how LLMs actually behave? We proved it does - and came up with the first solution to fix the distribution distortion problem.
If you’re around, I’d love to chat about these or just catch up! Drop by my poster sessions and let’s connect! Can’t wait to see everyone in Vancouver! 🇨🇦
Sep 25, 2024 Two first/co-first authored papers are accepted to NeurIPS 2024! 🎉🎉

publications (*equal contribution)

2024

  1. NeurIPS 2024
    Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
    Jiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang, Yixuan Li, and Neel Joshi
    Jun 2024
  2. NeurIPS 2024
    Grammar-Aligned Decoding
    Kanghee Park*, Jiayu Wang*, Taylor Berg-Kirkpatrick, Nadia Polikarpova, and Loris D’Antoni
    May 2024