Yuanliang Ju

Yuanliang(Avery) Ju | 鞠沅良

I am a CS Ph.D. student at University of Toronto and Vector Institute, advised by Prof. Florian Shkurti. After earning my bachelor's degree with honors, I did research with Prof. Li Yi at IIIS, Tsinghua University and Prof. Dan Xu at HKUST.

Email UofT: yuanliang.ju@mail.utoronto.ca
UofT CS: yuanliangju@cs.toronto.edu / Google Scholar / Github / Twitter

Publications
	RL²-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Derek Ming Siang Tan, Shailesh Shailesh, Srikrishna Iyer, William Wei Jie Teo, Yuanliang Ju, Qiao Gu, Guillaume Sartoretti ArXiv / Project Page / Code / Models / Video Under reviewing
	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, CoRL, 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)

This homepage is designed based on Jon Barron's website and deployed on Github Pages.
@ Yuanliang Ju

Publications
	RL²-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Derek Ming Siang Tan, Shailesh Shailesh, Srikrishna Iyer, William Wei Jie Teo, Yuanliang Ju, Qiao Gu, Guillaume Sartoretti ArXiv / Project Page / Code / Models / Video Under reviewing
	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