Qian Luo (罗谦)

I am Qian Luo, a 1st-year Data Science Ph.D. student at University of Hong Kong advised by Prof. Yanchao Yang.

Previously I worked as a research associate at Shanghai Qi Zhi Institute advised by Prof. Yi Wu. Prior to that, I was a NLP algorithm engineer at Alibaba Group.

I received my M.S. Degree from Georgia Institute of Technology in 2021, where I was advised by Prof. Sehoon Ha. I also worked closely with Prof. Dhruv Batra.

Email  /  Google Scholar  /  LinkedIn  /  Github  / 

profile photo
Research

My research interest lies in building up the Embodied AI system with less human supervision and has better adaptability in our real world. My current research involves training robust robot policies via foundational models and unsupervised concept discovery.

InfoCon: Concept Discovery with Generative and Discriminative Informativeness
Ruizhe Liu, Qian Luo, Yanchao Yang
ICLR, 2024

paper  /  code

Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning
Tianbao Xie*, Siheng Zhao*, Chen Henry Wu, Yitao Liu*, Qian Luo, Victor Zhong, Yanchao Yang, Tao Yu
ICLR, 2024   (Spotlight)

paper  /  code  /  project page

Grounding Object Relations in Language-Conditioned Robotic Manipulation with Semantic-Spatial Reasoning
Qian Luo*, Yunfei Li*, Yi Wu
AAAI RL Ready for Prod Workshop, 2023

Contrastive Code-Comment Pre-training
Xiaohuan Pei, Daochang Liu, Qian Luo, Chang Xu
ICDM, 2022   (Best Student Paper Award - 1/870)

paper  /  code

Benchmarking augmentation methods for learning robust navigation agents: the winning entry of the 2021 igibson challenge
Naoki Yokoyama*, Qian Luo*, Dhruv Batra, Sehoon Ha
IROS, 2022

paper  /  challenge page  /  video

A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning
Qian Luo, Maks Sorokin, Sehoon Ha
ICRA, 2021

paper  /  video

A generalized robotic handwriting learning system based on dynamic movement primitives (DMPs)
Qian Luo*, Jing Wu*, Matthew Gombolay
ArXiv, 2020

paper  /  video

Template borrowed from Jon Barron.