Yiming Tang

About Me

Hi! I'm Yiming, a second-year PhD student in National University of Singapore, very fortunate to be advised by Prof. Dianbo Liu. My research primarily aims to develop algorithms and theories toward a better understanding of intelligence, currently focusing on the identification of human-interpretable concepts encoded in machine learning models and the human brain. During my undergraduate studies, I was very lucky to collaborate with Prof. Bin Dong, Prof. Shanghang Zhang, and Prof. Hao Dong.

News

• [2024.10] One paper accepted in International Conference on Machine Learning (SAN) 🎉
• [2024.3] One paper accepted in European Conference on Computer Vision (LLM Dataset Analyst) 🎉
• [2023.10] One paper accepted in Journal of Machine Learning (PE Lens) 🎉

Research Interests

My research interests focus on:

• Mechanistic Interpretability: Understanding the internal representation space of machine learning models by identifying specific concepts encoded within them.
• Medical AI Transparency: Developing interpretable diagnostic systems that enhance clinical trust and improve healthcare outcomes, as one solid application of model interpretability.

Beyond these two types of works, these topics are also within my interests: vision-language models, compositional generalization, AI agents, AI safety, and neuroscience (especially fMRI and EEG).

Collaboration

I'm actively looking for collaboration in mechanistic interpretability, machine learning theory, and AI for medicine. I can offer research intern positions for undergraduates and master students interested in relevant research topics. Feel free to contact me directly via email or WeChat.

Selected Works

On the Theoretical Foundation of Sparse Dictionary Learning in Mechanistic Interpretability

We develop a theoretical framework for sparse dictionary learning in mechanistic interpretability.

Paper

How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders

We develop matryoshka transcoders and utilize it to identify physical plausibility failure modes of generative models, achieving SOTA performances.

Paper

Human-like Content Analysis for Generative AI with Language-Grounded Sparse Encoders

We develop LanSE and decompose natural and medical images into interpretable visual patterns grounded in natural language, supporting fine-grained analysis on AI generated contents.

Paper

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model

We are the first in the literature to prompt engineer LLMs to inspect datasets and analyze their subpopulation structures.

Paper

Prompt Engineering Through the Lens of Optimal Control

We are one of the first approaches to develop a theoretical framework to understand various prompt engineering methods through the lens of rigorous optimal control theory.

Paper

Introducing Brainiac Buddy, your AI-powered teaching assistant

It was a real honor to participate in the early development of Brainiac Buddy, an AI-powered teaching assistant with real-world applications in Peking University developed by Bin Dong's team.

Project

The Integrated Forward-Forward Algorithm: Integrating Forward-Forward and Shallow Backpropagation with Local Losses

We follow Hinton's Forward-Forward algorithm and make it applicable for deeper layers via the introduction of local losses.

Paper

Publications and Preprints

For a complete list of publications, please visit my Google Scholar profile.

Education

National University of Singapore

Doctor of Philosophy, College of Design and Engineering

Peking University

Bachelor of Science, School of Mathematical Sciences

Talks

Experiences

Research Associate

Cognitive AI for Science Lab, National University of Singapore

August 2024 - Present

Supervisor: Dianbo Liu

Research Intern

Beijing International Center for Mathematical Research, Peking University

2023 - 2024

Supervisor: Bin Dong

Research Intern

Human Machine Intelligence Lab, Peking University

2023 - 2024

Supervisor: Shanghang Zhang

Research Intern

Hyperplane Lab, Peking University

2021 - 2022

Supervisor: Hao Dong

Teaching Researcher

Beijing Aijianzi Education Technology Co., Ltd., Beijing

2019 - 2021

Supervisor: Xiaojun Hu

Mentorship

I have had the privilege of mentoring several students working on research topics in Mechanistic Interpretability and AI for Biomedical Sciences. One of my favorite parts of research is meeting and collaborating with people from diverse backgrounds.

Harshvardhan Saini

Indian Institute of Technology, India

Zheng Lin

Hong Kong University of Science and Technology, Hong Kong

Zhaoqian Yao

Chinese University of Hong Kong, Hong Kong

Qinglin Qi

Lund University, Sweden

Meet Desmond

It is such an honor and a great pleasure to introduce to you here my black cat cyber pet, Desmond. You are cordially invited to pat Desmond and chat with him!

Pat Desmond Have a Chat!

Desmond is Tired! You Have Reached Maximum Patting Times per Visit. Come Back Later or Subscribe to Desmond Pro for Unlimited Pats (>w<).

Wellcome, visitor! Master is out, let us talk. 🐱

Send