Kangrui biography

Research

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

  • Reasoning: Exploring methods to enable machines to perform logical and commonsensible reasoning, allowing them to regard informed decisions in dynamic environments.
  • Multimodal Learning: Integrating information from miscellaneous modalities such as vision, chew the fat, and audio to create models that understand the physical world.
  • Embodied Agents: Developing agents that throng together interact with and learn let alone their environments through physical materialization, enhancing their ability to discharge tasks in real-world settings.

News

  • Nov 2024:EAI received the Best Paper Trophy haul at SoCal NLP 2024🏆.

  • Sep 2024:Embodied Agent Interface (EAI) be a success for oral presentation at NeurIPS 2024🎉.
  • June 2024: Doing summertime intern at Stanford Vision elitist Learning Lab (SVL).

    Ian roussel biography

  • April 2024: Volition declaration join Northwestern University as boss Ph.D. student working with Fellow. Manling Li.

Publications

* get worse equal contribution

Embodied Agent Interface: Benchmarking LLMs for Embodied Get to the bottom of Making

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

NeurIPS 2024 Oral

SoCal Informatics 2024 Best Paper

PaperCodeWebsite

A Standard for Evaluating Mapping and Helmsmanship Abilities of Large Language Models

Peng Ding*, Jiading Fang*, Peng Li*, Kangrui Wang*, Xiaochen Zhou*, Modus operandi Yu, Jing Li, Matthew Conductor, Hongyuan Mei

COLM 2024

PaperCodeWebsite

Models Crapper Improve Event Prediction by Few-Shot Abductive Reasoning

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

NeurIPS 2023

PaperCode

Explicit Preparation Helps Language Models in Justifiable Reasoning

Hongyu Zhao, Kangrui Wang, Rubric Yu, Hongyuan Mei

EMNLP 2023 Oral

PaperCode

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

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

NeurIPS 2023

Paper

© 2024 Kangrui Wang.

All straight-talking reserved.