|
Yuanliang(Avery) Ju | 鞠沅良
I am a CS Ph.D. student at University of Toronto and Vector Institute,
where I am fortunate to be advised by Prof. Florian Shkurti.
After obtaining my bachelor's degree with honors, I did research with Prof. Li Yi at
IIIS, Tsinghua University
and Prof. Dan Xu at
The Hong Kong University of Science and Technology,
I am deeply grateful to all my advisors for their patient guidance and support, which allowed me to have a fulfilling and wonderful gap year!
My research interests are in Robotics and Computer Vision, with a particular focus on robotic dexterous manipulation. I am passionate about building real-world robotic systems, and my goal is to develop robots that can perceive and understand the physical world, and interact with it with human-level dexterity in complex, unstructured environments.
Email
UofT: yuanliang.ju@mail.utoronto.ca
UofT CS: yuanliangju@cs.toronto.edu
/
Google Scholar /
Github /
WeChat
|
|
News
[2026/07] 🥰 I will be attending ICML 2026 in person, see you in Seoul, Korea 🇰🇷!
[2026/04] 🎉 One paper gets accepted to ICML 2026 as Spotlight, Top 2%.
[2026/01] 🎉 One paper gets accepted to ICLR 2026 as Oral, Top 1%.
[2025/09] 🎉 One paper gets accepted to NeurIPS 2025.
[2024/12] 🥰 I will be attending NeurIPS 2024 in person, see you in Vancouver, Canada 🇨🇦!
[2024/10] 🥰 We release 3DGS-DET.
[2024/09] 🎉 One paper gets accepted to NeurIPS 2024.
|
Publications
|
Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning
Nandiraju Gireesh,
Yuanliang Ju,
He Wang†
ArXiv
Under reviewing
|
|
HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks
Nandiraju Gireesh*,
Yuanliang Ju*,
Chaoyi Xu,
Weiheng Liu,
Yuxuan Wan,
He Wang†
ArXiv
/
Project Page
ICML 2026 Spotlight, Top 2%
|
|
MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning
Yuanchen Ju*,
Yongyuan Liang*,
Yen-Jen Wang*,
Gireesh Nandiraju,
Yuanliang Ju,
Seungjae Lee,
Qiao Gu,
Elvis Hsieh,
Furong Huang†,
Koushil Sreenath†
ArXiv
/
Project Page
/
Code
/
Twitter
ICLR 2026 Oral, Top 1%
|
|
SAFE: Scalable Failure Estimation for Vision-Language-Action Models
Qiao Gu,
Yuanliang Ju,
Shengxiang Sun,
Igor Gilitschenski,
Haruki Nishimura,
Masha Itkina,
Florian Shkurti†
ArXiv
/
Project Page
/
Code
/
Twitter
NeurIPS 2025
|
|
3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection
Yang Cao*,
Yuanliang Ju*,
Dan Xu†
ArXiv
/
Code
|
|
ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images
Timing Yang*,
Yuanliang Ju*,
Li Yi†
ArXiv
/
Project Page
/
Code
/
Twitter
NeurIPS 2024
|
Services
Reviewer: ICLR, NeurIPS, CVPR, ICCV, ECCV, BMVC
TA: CSC343H1F - Introduction to Databases
TA: CSC303H1S - Social and Information Network
|
Selected Awards and Honors
2020 National Scholarship (Highest Honor for undergraduates in China)
2022 National Scholarship (Highest Honor for undergraduates in China)
|
Miscellaneous
Some interesting things worth recording here:
I have a twin sister named Yuanchen Ju(鞠沅辰). Our names, "Liang Chen (良辰)", symbolize propitious times. After some early exploration, I found my way to robotics as well, and I am glad we now share the same research passion.
Apart from my research, I like playing badminton, cycling, cooking, solving Rubik's cubes, painting, and photography. These activities bring relaxation and joy to my life.
I am of Mongolian ethnicity, ᠲᠡᠪᠴᠢᠶᠡᠷ ᠨᠢ ᠬᠦᠴᠦᠨ is one of my favorite proverbs in Mongolian.
I am a big fan of White Collar and Big Mistakes.
My MBTI bounces between ENTJ  and INTJ  .
|
This homepage is designed based on Jon Barron's website and deployed on Github Pages.
Last updated:  April 26, 2026 @ Yuanliang Ju 
|
