Kangrui Wang - Academic Website

Research

I am driven by a vision to develop advanced agents that can efficiently perform complex real-world tasks. In pursuit of this, my current research focuses on:

Reasoning: Exploring methods to enable machines to perform logical and commonsense reasoning, allowing them to make informed decisions in dynamic environments.
Multimodal Learning: Integrating information from multiple modalities such as vision, language, and audio to create models that understand the physical world.
Embodied Agents: Developing agents that can interact with and learn from their environments through physical embodiment, enhancing their ability to perform tasks in real-world settings.

News

Nov 2024:Embodied Agent Interface received the Best Paper Award at SoCal NLP 2024🏆.
Sep 2024:Embodied Agent Interface accepted for oral presentation at NeurIPS 2024🎉.
June 2024: Doing summer intern at Stanford Vision and Learning Lab (SVL).
April 2024: Will join Northwestern University as a Ph.D. student working with Prof. Manling Li.

Publications

* means equal contribution

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making

Manling Li*, Shiyu Zhao*, Qineng Wang*, Kangrui Wang*, Yu Zhou*, Sanjana Srivastava, Cem Gokmen, Tony Lee, Li Erran Li, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei, Jiayuan Mao, Jiajun Wu

NeurIPS 2024 Oral

Paper Code Website

A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models

Peng Ding*, Jiading Fang*, Peng Li*, Kangrui Wang*, Xiaochen Zhou*, Mo Yu, Jing Li, Matthew Walter, Hongyuan Mei

COLM 2024

Paper Code Website

Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Xiaoming Shi, Siqiao Xue, Kangrui Wang, Fan Zhou, James Zhang, Jun Zhou, Chenhao Tan, Hongyuan Mei

NeurIPS 2023

Paper Code

Explicit Planning Helps Language Models in Logical Reasoning

Hongyu Zhao, Kangrui Wang, Mo Yu, Hongyuan Mei

EMNLP 2023 Oral

Paper Code

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities

Dongrui Liu, Huiqi Deng, Xu Cheng, Qihan Ren, Kangrui Wang, Quanshi Zhang

NeurIPS 2023

Paper