Litian Liang
梁力天
About me
I'm a Visiting Student in REAL lab at Stanford, advised by Prof. Shuran Song. My research focuses on 3D vision for Embodied AI.
I received my M.S. in Computer Science from UC San Diego, where I worked on computer vision and embodied AI with 3D vision in Prof. Hao Su's lab.
I received my B.S. in Computer Science from UC Irvine, where I worked in Intelligent Dynamics Lab with Prof. Roy Fox and Prof. Alexander Ihler on Deep Reinforcement Learning.
I was born and raised in Beijing. Me and my family live very close to Beijing Jiaotong University.
email: l6liang <at> ucsd <dot> edu
Resume / Google Scholar / GitHub / Linkedin / Twitter
Research goals
The goal of my research is to enable AI to perform tedious or dangerous tasks like cleaning, cooking, driving, etc, safer and more efficient than any human ever existed in this world can do. Then we will be free to do more interesting things like art, music, math, and science.
Research interests
Probabilistic Inference and Learning
Imitation Learning, Reinforcement Learning
Computer Vision, Robotics Control
Research
Robo360: A 3D Omnispective Multi-Material Robotic Manipulation Dataset
Litian Liang, Liuyu Bian, Caiwei Xiao, Jialin Zhang, Linghao Chen, Isabella Liu, Fanbo Xiang, Zhiao Huang, Hao Su
Preprint
Keywords: 1. Real-World Dataset, 2. Robotic Manipulation
Paper / Video / Teleoperation / Code and data coming soon
We collected a large-scale real-world dataset of robot manipulation of objects with diverse optical and material variations from omnispective view directions using 86 DSLR cameras. We demonstrated the quality of Robo360 dataset by showing you can not only learn robot policies with imitation learning but also achieve high-quality reconstruction of the scene in 3D. We hope that Robo360 can open new research directions yet to be explored at the intersection of understanding the physical world in 3D and robot control.
Work done at Hao Su Lab @ UC San Diego
Reparameterized Policy Learning for Multimodal Trajectory Optimization
Zhiao Huang, Litian Liang, Zhan Ling, Xuanlin Li, Chuang Gan, Hao Su
ICML 2023 Oral Presentation
Keywords: 1. continuous action space, 2. dense reward with local optima, 3. sparse reward exploration
Paper / Code / Project Page / Video
We proposed a novel policy parameterization that significantly improves performance in maximizing with a dense reward that contains local optima and exploring sparse reward (sparse 0/1 reward) with intrinsic rewards (RND). Our novel approach solves hard sparse reward exploration tasks that were previously believed to be impossible to solve by RL methods.
Work done at Hao Su Lab @ UC San Diego
Reducing Variance in TD Value Estimation via Ensemble of Deep Networks
Litian Liang, Yaosheng Xu, Stephen McAleer, Dailin Hu, Alexander Ihler, Pieter Abbeel, Roy Fox
ICML 2022
Keywords: 1. TD value estimation bias and variance, 2. ensemble value estimator
We investigate and propose a specific combination of existing techniques to improve sample efficiency in learning a value network with TD. The combination achieved enough stability during training to obviate the target network. This method is applicable to any value network that optimizes TD error.
Work done at Intelligent Dynamics Lab @ UC Irvine
Service
Reviewer: IEEE / CVF Computer Vision and Pattern Recognition (CVPR 2024)
Awards
Chancellor's Award for Excellence in Undergraduate Research
Highest honor awarded to undergraduate student at UC Irvine for research dedication and accomplishments.
Misc
I love watching movies. My favorite movie list:
Interstellar, Inception, The Imitation Game, Oppenheimer, The Matrix series.