|
I am a PhD student in Computer Science at Princeton University, advised by Olga Russakovsky. Previously, I received my bachelor degree in Applied Mathematics and Data Science from UC Berkeley. I did research as part of Berkeley Artificial Intelligence Research, where I was advised by Kimin Lee, Aditi Raghunathan, and Pieter Abbeel. Email / Resume / Google Scholar / Twitter / Github |
|
|
I'm currently working on generative models and its applications in computer vision. Previously, I also worked on deep reinforcement learning and embodied AI. |
|
Xinran Liang, Esin Tureci, Prachi Sinha, Ye Zhu, Vikram Ramaswamy, Olga Russakovsky under review, 2024 We introduce a dataset augmentation method that uses text-to-image generative models for contextual debiasing by adapting personalized finetuning of diffusion models. |
  |
Xinran Liang, Anthony Han, Wilson Yan, Aditi Raghunathan, Pieter Abbeel arxiv preprint, 2023 paper / website / code An embodied learning framework based on active exploration for visual representations and perception tasks. We propose to learn representations from action signals implicitly through reinforcement learning and explicitly via inverse dynamics prediction. |
|
Xinran Liang, Katherine Shu, Kimin Lee*, Pieter Abbeel* International Conference on Learning Representations (ICLR), 2022 paper / code We propose a simple and efficient human-guided exploration method by measuring uncertainty in human instructions as intrinsic rewards. |
|
|
|
|
CS 324: Introduction to Machine Learning
CS 226: Algorithms and Data Structures
|
|
Data 140: Probability for Data Science
|
|
Data 100: Principles and Techniques of Data Science |
|
Redesigned from Jon Barron's source code. |