LAB LOGA page on LabLog, a review site (not the lab's official page)
Structured Intelligence Lab
Machine-translated · View original
The lab designs deep learning by building knowledge of mathematics and physics into it.
AboutAbout the lab
Applying mathematics and physics to cutting-edge AI development
The Structured Intelligence Lab develops new AI technologies centered on deep learning, drawing on mathematics such as analytical mechanics and differential geometry.
A distinctive feature of deep learning is that mathematical structure can be built in when the network is designed.
Taking advantage of this property, the lab works on AI simulators that enable fast computer simulation, and on generative AI that creates images matching a given text.
The lab holds research presentations, reading groups, and study sessions, and welcomes participation in its study sessions and projects.
Key terms
- Deep learning
- A method in which a multilayer network modeled on the connections between neurons in the brain learns features from many examples
- Differential geometry
- A field of mathematics that uses differentiation and integration to study the shapes of curved surfaces and spaces
- Generative AI
- AI that creates new content, such as text and images, based on the data it has learned from
NewsLab news
A paper by a master's student accepted at the international conference ECCV 2026
Two papers accepted at the international conference ICLR 2026
A paper by a master's student accepted at the international conference AAAI 2026
A paper on robot control from images accepted in the English-language journal of the Institute of Electronics, Information and Communication Engineers (IEICE)
ResearchResearch themes
The lab develops new AI technologies centered on deep learning, based on mathematics such as analytical mechanics and differential geometry. From AI that speeds up computer simulation to generative AI that creates images matching a given text, it covers both theoretical analysis and applications.
*Illustrative imageDeep Geometric Mechanics
The lab incorporates ideas from analytical mechanics and differential geometry into deep learning to model, from data, physical phenomena whose detailed equations are not known. The aim is fast, accurate simulation that preserves the law of energy conservation.
*Illustrative imageOperator Learning
The lab works on PINNs (physics-informed neural networks), a method that represents solutions of partial differential equations with neural networks. By introducing a way of choosing lattice points based on number theory, it made training roughly 2 to 7 times faster for low-dimensional equations.
*Illustrative imageGeometry and Structure of Semantic Spaces
Focusing on the geometry of the spaces in which images and text are embedded, the lab builds representation learning that can express both the hierarchy and the composition of concepts, as well as mechanisms for generating images that are faithful to written instructions.
*Illustrative imageGeometry of Data Spaces
Using the shapes and connections inherent in the data itself as clues, the lab studies methods for generating 3D point clouds and for smoothly connecting images produced by diffusion models.
MembersFaculty
The members of the Structured Intelligence Lab consist of faculty, project researchers, secretaries, doctoral, master's, and undergraduate students, and research students.As of 2026
- ProfessorTakashi Matsubara
- Associate ProfessorLing Xiao
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Structured Intelligence Lab
Knowledge Base LabFaculty of Engineering, Department of Information and ElectronicsTheoretical and experimental research on knowledge discovery…
Large-Scale Knowledge Processing LabFaculty of Engineering, Department of Information and ElectronicsUltrafast processing of large-scale data in machine learning…
Human-Computer Interaction LabFaculty of Engineering, Department of Information and ElectronicsHuman-centered interactive systems (HCI/HRI/HAI/xR/UI/UX/mac…
Integrated Nanosystems LabFaculty of Engineering, Department of Information and ElectronicsCreation of novel information science and technology through…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Costa's Minimal Surface” Anders Sandberg / CC BY-SA 3.0 (cropped)
- Deep Geometric Mechanics: “Surface waves” Roger McLassus / CC BY-SA 3.0 (cropped)
- Operator Learning: “Chladni plate 10” Exhibit made by Estes Objethos Atelier, photo by Rodrigo Tetsuo Argenton / CC BY-SA 4.0 (cropped)
- Geometry and Structure of Semantic Spaces: “H2 tiling 334-1” Anton Sherwood / Public domain (cropped)
- Geometry of Data Spaces: “Ouster OS1-64 lidar point cloud of intersection of Folsom and Dore St, San Francisco” Daniel L. Lu / CC BY 4.0 (cropped)
- Related lab (Knowledge Base Lab): “UIUC Library Main Stacks” Chevsapher / CC0 (cropped)
- Related lab (Large-Scale Knowledge Processing Lab): “Network Visualization” Martin Grandjean / CC BY-SA 4.0 (cropped)
- Related lab (Human-Computer Interaction Lab): “Backlit keyboard” Colin / CC BY-SA 4.0 (cropped)
- Related lab (Integrated Nanosystems Lab): “Нейрон коры с множеством дендритных шипиков” Sergb95 / CC BY-SA 4.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.