Zirui Zhao
ziruiz [AT] comp.nus.edu.sg ryan_zzr [AT] outlook.com
Zirui Zhao is a PhD student in Computer Science at the National University of Singapore, advised by Prof. Wee Sun Lee. He also works closely with Prof. David Hsu. He is doing research on decision-making, reasoning, and their intersections with Machine Learning. During his PhD study, he worked as a research intern at Salesforce, hosted by Hanze Dong, Amrita Saha, and Doyen Sahoo. He received his Bachelor's Degree at Xi'an Jiaotong University. He used to work with Prof. Pengju Ren during his undergrad study and Prof. Ding Zhao when visiting CMU.
CV  / 
Google Scholar  / 
Github
|
|
-
Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
Zirui Zhao,
Hanze Dong,
Amrita Saha,
Caiming Xiong,
Doyen Sahoo
Preprint, 2024
arXiv
Auto-CEI pushes and estimates the limits of LLM reasoning capacities and aligns LLM's assertive and conservative response behaviours according to these limits for reliable reasoning.
-
On the Empirical Complexity of Reasoning and Planning in LLMs
Liwei Kang*,
Zirui Zhao*,
David Hsu,
Wee Sun Lee (*Equal contribution, listed in alphabetical order)
EMNLP Findings, 2024
arXiv
We propose an easy-to-use framework that leverages sample and computational complexity from machine learning theory to analyze reasoning and planning problems and to design/optimize LLM-based reasoning methods.
-
Large Language Models as Commonsense Knowledge for Large-Scale Task Planning
Zirui Zhao,
Wee Sun Lee,
David Hsu
NeurIPS, 2023
Also in RSS LTAMP Workshop, Best Paper Runner-up, 2023
project page /
arXiv /
code /
openreview /
bibtex
We use Large Language Models as both the commonsense world model and the heuristic policy within Monte Carlo Tree Search. LLM's world model provides with MCTS a commonsense prior belief of states for reasoned decision-making. The LLM's heuristic policy guides the search to relevant parts of the tree, substantially reducing the search complexity.
-
Differentiable Parsing and Visual Grounding of Natural Language Instructions for Object Placement
Zirui Zhao,
Wee Sun Lee,
David Hsu
ICRA, 2023
Also in CoRL LangRob Workshop, 2022
project page /
IEEE Xplore /
code /
video /
arXiv /
bibtex
We proposed ParaGon for language-conditioned object placing. ParaGon integrates a parsing algorithm into an end-to-end trainable neural network. It is data-efficient and generalizable for learning compositional instructions, and robust to noisy, ambiguous language inputs.
-
Active Learning for Risk-sensitive Inverse Reinforcement Learning
Rui Chen,
Wenshuo Wang,
Zirui Zhao,
Ding Zhao
Preprint, 2019
code /
arXiv
Risk-sensitive inverse reinforcement learning provides an general model to capture how human assess the distribution of a stochastic outcome when the true distribution is unknown (ambiguous). This work enables an RS-IRL learner to actively query expert demonstrations for faster risk envelope approximation.
-
Visual Semantic SLAM
Zirui Zhao, Yijun Mao, Yan Ding,
Pengju Ren, Nanning Zheng
CCHI, 2019
code /
arXiv
Semantic SLAM projecting semantic meaning into 3D point clouds generated by ORB SLAM algorithm.
Teaching
I am particularly interested in teaching, especially in the field of AI. I have been a teaching assistant for CS1010E (Programming Methodology), CS3245 (Information Retrieval), and teaching tutorials of CS3263 (Foundations of Artificial Intelligence) for two consecutive semesters. I was selected for the Teaching Fellowship Award in AY23/24-Sem1.
|
|