Dengzhe Hou

Dengzhe Hou

Assistant Professor @ Tohoku GSIS

Dengzhe Hou (侯登哲)

I am an Assistant Professor at Tohoku University, Japan.

My research spans AI4Brain (AI for understanding the brain) and Brain4AI (brain and cognitive science for understanding and improving AI).

Background & research interests

At the Graduate School of Information Sciences (GSIS), I am affiliated with the Yamada Laboratory and the International Liaison Office (ILO), with a concurrent appointment in the Social Integration Research Division of the Unprecedented-scale Data Analytics Center (UDAC).

I received my Ph.D. under Prof. Satoshi Shioiri at the Visual Cognition and Systems Laboratory, and was a Visiting PhD Scholar in the Sydney Cash Lab at Harvard Medical School / Massachusetts General Hospital.

My work focuses on two connected directions:

  • AI4Brain: Reliable decoding and automated analysis of EEG, including preprocessing-induced instability, per-trial uncertainty, and feature attribution; understanding self-initiated attention through EEG, eye tracking, and computational modeling.
  • Brain4AI: Drawing on cognitive neuroscience to understand, evaluate, and improve AI systems, with a focus on working memory, cumulative state tracking, and the structure of cognitive abilities in large language models.

Connecting these directions, my current work explores aligning brain signals (EEG, fMRI) with representations in large language and vision-language models.

Full CV

Selected Research

News

  
Sep 2026Invited talk at RSJ2026 Open Forum OF7, “テクノロジーの質的進化と組織統制”, 44th Annual Conference of the Robotics Society of Japan, Kanazawa. Speaking on neurotechnology with Michael Zielewski
Aug 2026Co-authored presentation accepted at the Japan Institute of Marketing Science (JIMS) Research Conference, Waseda University, 14–15 Nov 2026: “生成AI活用事例における社会倫理的リスクと炎上要因の定量分析”
Aug 2026Paper accepted at IEEE SMC 2026 (Bellevue, USA), Subject-Specific Analysis of Self-Initiated Attention Shifts from EEG
Aug 2026TimePre accepted at Transactions on Machine Learning Research (TMLR)
Aug 2026Awarded a research grant (PI) from GSIS, Tohoku University, under Interdisciplinary Research Project Development Support: 認知科学実験パラダイムに基づくAIシステム認知能力評価プラットフォームの開拓
Aug 2026New preprint on arXiv, Control-Diverse Reinforcement Fine-Tuning. RL post-training concentrates control on a shared set of components across tasks, even where activations look diverse — and relieving that bottleneck improves multi-task performance
Aug 2026Invited talk at the 12th Annual CWRU-Tohoku Data Science in Engineering and Life Sciences Symposium, Cleveland, USA: “From Preprocessing Choices to LLM Agents: Automated and Verifiable Cognitive EEG Analysis”
Aug 2026Awarded KAKENHI Grant-in-Aid for Research Activity Start-up (PI, 26K25566): the representational format of attentional templates, probed with computational model hierarchies, EEG and eye tracking
Earlier news
  
Aug 2026Kaggle Silver Medal in ROGII - Wellbore Geology Prediction (89/6125)
Jul 2026KANMixer published in Scientific Reports: a compact KAN-centered mixer for long-term forecasting, and an honest account of when KANs actually help
Jul 2026Two new preprints on arXiv: CogEEGAgent (autonomous cognitive EEG analysis) and CogArena (cognitive ability structure in LLMs)
Jul 2026Awarded a research grant (PI) from the Center for So-Go-Chi (Convergence Knowledge) Informatics, Tohoku University
Jul 2026Appointed to the Editorial Board of Interdisciplinary Information Sciences (Tohoku University GSIS)
Jun 2026Joined the Tohoku University × NTT DATA Group joint research on technology governance (TechGov) as a research member
Jun 2026PVIR poster presented at CVPR 2026 Workshop VGBE, Denver, Colorado
May 2026Joined the TechGov initiative at UDAC, Tohoku University
May 2026New preprint on arXiv, Subject-Specific Analysis of Self-Initiated Attention Shifts from EEG. SHAP-based within-subject decoding of self-initiated attention
May 2026New preprint on arXiv, Same Brain, Different Prediction. Preprocessing pipelines flip up to 42% of EEG decoding predictions, and we introduce a diagnostic and a regularization fix
May 2026Updated preprint. WMF-AM v2 reframes our LLM probe around working-memory depth and isolates cumulative state tracking as the dominant bottleneck
Apr 2026Collaborator on new preprint, Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work
Apr 2026Started as Assistant Professor at GSIS, Tohoku University (Yamada Lab, ILO) with concurrent appointment at UDAC Social Integration Research Division
Apr 2026Teaching Machine Learning Basics at GSIS, Tohoku University
Mar 2026Paper accepted at CVPR 2026 Workshop VGBE, Physics-Aware Video Instance Removal Benchmark
Mar 2026First version of the LLM working-memory probe on arXiv, then titled Beyond Completion: Probing Cumulative State Tracking to Predict LLM Agent Performance (later revised and retitled WMF-AM)
Feb 2026Participated in Qualia Structure Grant Meeting
Feb 2026Appeared in Journal Club: The Proliferation of Consciousness Theories: What can we do next? (Neural basis of Consciousness & Qualia Structure)
Dec 2025Paper published in Frontiers in Human Neuroscience, frontal-midline theta ramping indexes self-initiated attention shifts
Apr 2025Awarded JSPS DC2 Research Fellowship
Jan 2025Returned from visiting scholar position at Harvard Medical School / MGH (Sydney Cash Lab, supervised by Dr. Jing (Jill) Cai)
Dec 2024Best Presentation Award, 32nd Doctoral Student Presentation, Tohoku University
Oct 2024Presented two posters at Society for Neuroscience 2024
Jul 2024Two presentations at APCV 2024 (The 16th Asia Pacific Conference on Vision)
Aug 2023Oral presentation at ECVP 2023, Paphos, Cyprus; awarded ECVP Student Travel Award

Education

Ph.D. · Information Sciences

Apr 2023 – Mar 2026

Graduate School of Information Sciences, Tohoku University

Thesis, advisors & programs

M.S. · Information Sciences

Apr 2021 – Mar 2023

Graduate School of Information Sciences, Tohoku University

Advisors & program

B.Eng. · Electronic and Information Engineering

Sep 2016 – Jul 2020

Tongji University · Automation

Advisor & academic record

Teaching

Instructor, Graduate School of Information Sciences, Tohoku University

Machine Learning Basics

Apr 2026 – present

GSIS, Tohoku University · GPDS. Course materials adapted from Samy Baladram.

Data Science Training II & Data Science Challenge

Jun 2026 – Jul 2026

GSIS, Tohoku University

Teaching Assistant, Graduate School of Information Sciences, Tohoku University (2022 – 2025)

Supervisors: Prof. Kazunori Yamada, Assoc. Prof. Samy Baladram

  • Spring 2024: Machine Learning Basics, Data Science Programming Basics, Data Engineering, Data Science Training I & II
  • Fall 2023: Data Science Basics
  • Spring 2022: Data Science Training I, Data Science Skill Up Exercise

Grants, Fellowships & Awards

  
2026–2027KAKENHI Grant-in-Aid for Research Activity Start-up (PI, 26K25566): 注意テンプレートの表象形式：計算モデル階層・脳波・視線追跡による解明 (¥2,600,000)
2026Kaggle Silver Medal, ROGII - Wellbore Geology Prediction (89/6125), certificate
2026Research Grant (PI), Center for So-Go-Chi (Convergence Knowledge) Informatics, Tohoku University (¥400,000)
2026–Research Member, Tohoku University × NTT DATA Group Joint Research on Technology Governance (TechGov, UDAC) (¥1,000,000 individual allocation, of ¥40,000,000 total project)
2026Research Grant (PI), Interdisciplinary Research Project Development Support, Graduate School of Information Sciences (GSIS), Tohoku University: 認知科学実験パラダイムに基づくAIシステム認知能力評価プラットフォームの開拓 (¥500,000)
2026Kaggle Expert – Bronze Medal, CSIRO Image2Biomass Prediction (355/3805)
2025–2026JSPS DC2 Research Fellowship (completed)
2025Kaggle Bronze Medal, Santa 2024: The Perplexity Permutation Puzzle (148/1514)
2024–2028KAKENHI Grant-in-Aid for Scientific Research (A): 自発的脳機能の神経基盤理解 (PI: Prof. Satoshi Shioiri)
2024Best Presentation Award, 32nd Doctoral Student Presentation, Tohoku University
2023ECVP Student Travel Award
2023–2025JST Next Generation Researcher Challenging Research Program
2022–presentTohoku University GPDS Research Assistant
2021–2023Kamei Memorial Foundation Scholarship for International Students (公益財団法人亀井記念財団)
2016Tongji University Undergraduate Entrance Scholarship

Editorial Board

Reviewer

  • npj Science of Learning
  • Cognitive Neurodynamics
  • Journal of NeuroEngineering and Rehabilitation
  • Scientific Reports
  • Discover Neuroscience
  • European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2026)
  • International Joint Conference on Neural Networks (IJCNN)