Xiaolin Fang

Xiaolin Fang

Ph.D. Candidate, MIT
Email: xiaolinf [at] mit [dot] edu
Location: MIT Stata Center 45-64x
About me
I am a research scientist at Google DeepMind. I obtained my Ph.D. from MIT CSAIL, where I worked with Leslie Kaelbling and Tomás Lozano-Pérez.

My research focuses on robot learning and long-horizon planning, with an emphasis on generalizable policies across long-horizon tasks.
Selected Publications
[* indicates equal contribution]
[gemini robotics 1.5]
Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
Gemini Robotics Team
[Paper] [Blog Post]
[SFP]
Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
Sunshine Jiang, Xiaolin Fang, Nicholas Roy, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Siddharth Ancha
Oral Presentation, Conference on Robot Learning, CoRL, 2025
Best Paper Award Finalist, ICRA Workshop: Beyond Pick and Place, 2025
[Paper] [Website] [Code]
[Kalm]
KALM: Keypoint Abstraction using Large Models for Object-Relative Imitation Learning
Xiaolin Fang*, Bo-Ruei Huang*, Jiayuan Mao*, Jasmine Shone, Joshua B. Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling
IEEE International Conference on Robotics and Automation, ICRA, 2025
Best Paper Award, CoRL Workshop on Language and Robot Learning, 2024
[Paper] [Website] [Code]
[Uncos]
Embodied Uncertainty-Aware Object Segmentation
Xiaolin Fang, Leslie Pack Kaelbling, Tomás Lozano-Pérez
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS, 2024
[Paper] [Website] [Code]
[Dimsam]
DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability
Xiaolin Fang, Caelan Reed Garrett, Clemens Eppner, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Dieter Fox
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS, 2024
Best Conference Paper Award Finalist
Best Student Paper Award Finalist
[Paper] [Website]
[M0M]
Long-Horizon Manipulation of Unknown Objects via Task and Motion Planning with Estimated Affordances
Aidan Curtis*, Xiaolin Fang*, Leslie Pack Kaelbling, Tomás Lozano-Pérez, Caelan Reed Garrett
IEEE International Conference on Robotics and Automation, ICRA, 2022
[Paper] [Video] [Code]
[Condcoopnet]
Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
Jianwen Xie*, Zilong Zheng*, Xiaolin Fang, Song-Chun Zhu, Ying Nian Wu
IEEE Transactions on Pattern Analysis and Machine Intelligence, TPAMI, 2021
[Paper] [Website] [Code] [Code]
[CycleCoopnet]
Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
Jianwen Xie*, Zilong Zheng*, Xiaolin Fang, Song-Chun Zhu, Ying Nian Wu
Annual AAAI Conference on Artificial Intelligence, AAAI, 2021
[Paper] [Website] [Code]
[Triangle]
Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inferential Model
Tian Han*, Erik Nijkamp*, Xiaolin Fang, Mitch Hill, Song-Chun Zhu, Ying Nian Wu
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019
Oral Presentation
[Paper] [Website] [Code]