People
Who builds Flex-RSI
Flex-RSI is a community effort. Organizers run the benchmark and its protocol, contributors bring the tasks, evaluators and runs it is made of, and advisors guide its direction.
01Organizers
Jingdong ZhangPh.D. student · Texas A&MSpatial intelligence foundation models: scene understanding and multi-modal agents.
Jionghao WangPh.D. student · Texas A&MRobot foundation models, physics-based motion and 3D real-to-sim.
Zhengming YuPh.D. student · Texas A&MVideo generation, generative models and 3D vision & graphics.
02Contributorsin alphabetical order
Yancheng CaiPh.D. student · University of CambridgePerceptual image and video quality, multimodal LLMs and video generation.
Wei ChowNational University of SingaporeVision-language models and generative AI: text-to-image generation and image editing.
Chris ChoySenior Research Scientist · NVIDIA3D computer vision, scene understanding and geometric deep learning.
Zhiyang DouPh.D. student · MIT CSAILPhysics-based simulation, robotics, physical AI and character animation.
Hang HuaResearch Scientist · MIT‑IBM Watson AI LabVision-language foundation models, multimodal agents and world models.
Jiachen LiPh.D. student · UT AustinControl, robotics and optimization for safe, data-efficient autonomy.
Zhixuan LiuPh.D. student · Carnegie Mellon UniversityVisual generative models and robotics; controllable text-to-video.
Chen WangPh.D. student · University of Pennsylvania3D vision and graphics: reconstruction and generation of scenes.
Songlin WeiPh.D. student · University of Southern CaliforniaFoundation models for humanoids and benchmarking-oriented simulation.
Siyuan YangPh.D. student · Texas A&MHuman-centric video generation and editing with controllable video models.
Yu YuanPh.D. student · Purdue UniversityPhysics-consistent, controllable generative worlds and world models.
Xiaohang ZhanSenior Research Scientist 2 · AdobeVisual understanding, reasoning, generation and editing.
Yucheng ZhangPurdue UniversityKnowledge graphs, graph learning and large language models for relational data.
Shuhong ZhengPh.D. student · University of Toronto3D understanding and 3D/4D generation with multimodal foundation models.
03Advisorsin alphabetical order
Xin LiProfessor · Texas A&MReconstructing, generating and understanding 3D shapes, humans and worlds.
Lingjie LiuAssistant Professor · University of Pennsylvania3D/4D reconstruction, world modeling, neural rendering and humanoid robotics.
Wojciech MatusikProfessor · MIT CSAILAI for the physical world: designing and fabricating materials, devices and robots.
Zhengzhong TuAssistant Professor · Texas A&MGenerative and multimodal AI for driving, robotics, healthcare and science.
Wenping WangProfessor · Texas A&MComputer graphics, computer vision, machine learning and geometric modeling.
04Affiliations
MIT-IBM Watson
AI Lab
