Amber Xie

I am a PhD student at Stanford. My research is supported by the NDSEG Fellowship. I was also awarded the NSF Graduate Research Fellowship.

Previously, I graduated from UC Berkeley with an MS in Computer Science and BA in Computer Science and Applied Math. I was fortunate to be advised by Pieter Abbeel, Stephen James, and Youngwoon Lee at BAIR.

Contact: amberxie@stanford.edu
Google Scholar  /  Twitter  /  GitHub

profile photo
Research

I'm interested in robot learning. In particular, I would like to build intelligent, adaptable, multi-purpose robots that can learn quickly and accomplish complex tasks. I've worked on a variety of projects in deep reinforcement learning, imitation learning, and generative models to this aim.

LDP Latent Diffusion Planning for Imitation Learning
Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn
paper / website / code

We propose Latent Diffusion Planning (LDP), a modular approach consisting of a planner which can leverage action-free demonstrations, and an inverse dynamics model which can leverage suboptimal data, that both operate over a learned latent space.

LAPP Language-Conditioned Path Planning
Amber Xie, Youngwoon Lee, Pieter Abbeel, Stephen James
CoRL 2023 Conference on Robot Learning, 2023
paper / website / code / video

We propose the domain of Language-Conditioned Path Planning (LAPP), where contact-awareness is incorporated into the path planning problem. As a first step, we propose Language-Conditioned Collision Functions (LACO).

LAMP Language Reward Modulation for Pretraining Reinforcement Learning
Ademi Adeniji, Amber Xie, Carmelo Sferrazza, Younggyo Seo, Stephen James, Pieter Abbeel
paper / code

LAMP pretrains a language-conditioned agent without human supervision using noisy VLM rewards and unsupervised reinforcement learning.

vectorfusion VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
Ajay Jain*, Amber Xie*, Pieter Abbeel
CVPR 2023 The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
paper / website / gallery

VectorFusion generates infinitely scalable vector graphics (SVGs), pixel art and sketches from text using the pretrained Stable Diffusion model.

IRM Skill-Based Reinforcement Learning with Intrinsic Reward Matching
Ademi Adeniji*, Amber Xie*, Pieter Abbeel
paper / code

IRM leverages the skill discriminator from unsupervised RL pretraining to perform environment-interaction-free skill sequencing for unseen downstream tasks.

sim2seg Sim2Seg: End-to-end Off-road Autonomous Driving without Real Data
John So*, Amber Xie*, Sunggoo Jung, Jeffrey Edlund, Rohan Thakker, Ali-akbar Agha-mohammad, Pieter Abbeel, Stephen James
CoRL 2022 Conference on Robot Learning, 2022
paper / website / code / method vid / real-world vid

Segmentations are a concise, compressed representation for images. We show sim-to-real transfer through training an RL agent on image segmentations for off-road autonomous driving.

maugs Math Augmentation: How Authors Enhance the Readability of Formulas using Novel Visual Design Practices
Andrew Head, Amber Xie, Marti Hearst
CHI 2022 ACM Conference on Human Factors in Computing Systems, 2022
paper / video

We describe how authors alter the presentation of math formulas to make them more approachable, from colorization to labels, layout, and beyond.

🏆 Best Paper Award

Website template from Jon Barron