Bingbin Liu

PhD Student at Carnegie Mellon University
bingbinl [at] cs [dot] cmu [dot] edu
LinkedIn / Github / Google Scholar / CV (Feb 2024)

Welcome to my website! ^ ^ I am a PhD student at the Machine Learning Department of Carnegie Mellon University co-advised by Prof. Pradeep Ravikumar and Prof. Andrej Risteski. My main research focus is understanding discrete "reasoning" tasks. I am also interested in the theoretical understanding of self-supervised and unsupervised learning, often motivated by findings in vision and language. I am also broadly interested in theoretical aspects of machine learning in general.

Previously, I was a master student in the Stanford Vision and Learning Lab, where I worked on video understanding and its applications to healthcare under the supervision of Prof. Fei-Fei Li, Prof. Juan Carlos Niebles, and Prof. Serena Yeung.

Here are some slides from my recent talk which may provide more information about my work.

Preprints and Publications

(Un)interpretability of Transformers: a case study with bounded Dyck grammars
Kaiyue Wen, Yuchen Li, Bingbin Liu, Andrej Risteski

Masked prediction tasks: a parameter identifiability view
Bingbin Liu, Daniel Hsu, Pradeep Ravikumar, Andrej Risteski
NeurIPS 2022

Analyzing and improving the optimization landscape of noise-contrastive estimation
Bingbin Liu, Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
ICLR 2022 (spotlight) [blog post]

Contrastive learning of strong-mixing continuous-time stochastic processes
Bingbin Liu, Pradeep Ravikumar, Andrej Risteski

Generalized Boosting
Arun Sai Suggala, Bingbin Liu, Pradeep Ravikumar
NeurIPS 2020

A Computer Vision System to Detect Bedside Patient Mobilization
Serena Yeung*, Francesca Rinaldo*, Jeffrey Jopling, Bingbin Liu, Rishab Mehra, Lance Downing, Michelle Guo, Gabriel Bianconi, Alexandre Alahi, Julia Lee, Brandi Campbell, Kayla Deru, William Beninati, Li Fei-Fei, Arnold Milstein.
Nature Digital Medicine, 2019

Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos
Bingbin Liu, Serena Yeung, Edward Chou, De-An Huang, Li Fei-Fei, Juan Carlos Niebles
European Conference on Computer Vision (ECCV), 2018
Also presented at Women in Computer Vision (WiCV) workshop.
Paper Project page Poster Video

Learning to Decompose and Disentangle Representations for Video Prediction
Jun-Ting Hsieh, Bingbin Liu, De-An Huang, Li Fei-Fei, Juan Carlos Niebles
Neural Information Processing Systems (NeurIPS), 2018
Paper Github Poster Video

3D Point Cloud-Based Visual Prediction of ICU Mobility Care Activities
Bingbin Liu*, Michelle Guo*, Edward Chou, Rishab Mehra, Serena Yeung, N. Lance Downing, Francesca Salipur, Jeffrey Jopling, Brandi Campbell, Kayla Deru, William Beninati, Arnold Milstein,
Machine Learning for Health Care (MLHC), 2018


Teaching: When at Stanford, I was a teaching assistant for CS231n: Convolutional Neural Networks for Visual Recognition in Spring 2018 and Spring 2019, and the ICU project lead for MED277/CS377: AI-Assisted Healthcare.
I also had a great time working with some talented high school girls who are starting to learn coding. I helped at Girls teach Girls to Code (GTGTC) in April 2018 as the mentor lead of the AI team. I worked with Rob Voigt as research mentors for the NLP team at Stanford AI4ALL in summer 2018, where we worked with an amazing team of 8 girls on a project applying NLP techniques on Tweets to help with identifying resources for disaster relief. If you are interested in learning more about the role identities play in tech industries, please check out the website of Morgan Ames, a postdoc researher who observed the AI4ALL camps and is really nice to talk to. :)

Internship: I joined the Enterprise and Analytics team as a Group IT intern at CLP Power Hong Kong Limited in summer 2016, and was a software engineering intern at Hututa in summer 2015.

Misc: Some photos of Pittsburgh.