Details of the Researcher

PHOTO

Dengzhe Hou
Section
Graduate School of Information Sciences
Job title
Specially Appointed Assistant Professor(Research)
Degree

  • Bachelor (Tongji University)

  • Master (Tohoku University)

  • PhD (Tohoku University)

e-Rad No.
71039427
Profile

Assistant Professor at the Graduate School of Information Sciences, Tohoku University (Yamada Laboratory; International Liaison Office), with a concurrent appointment at the Unprecedented-scale Data Analytics Center (UDAC), Social Integration Research Division (from April 2026). Former JSPS DC2 Research Fellow (2025–2026). Research spans AI4Cog (AI for cognitive science), Cog4AI (cognitive science for AI), AI4Brain (AI for neuroscience) and Brain4AI (neuroscience for AI), including reliable EEG decoding, self-initiated attention, cognitive evaluation of language and decision models, and brain–AI representation alignment. Ph.D. in Information Sciences, Tohoku University (2026).

Research History 4

  • 2026/04 - Present
    Tohoku University　Unprecedented-scale Data Analytics Center

  • 2026/04 - Present
    Tohoku University　Graduate School of Information Sciences

  • 2025/04 - 2026/03
    Japan Society for the Promotion of Science　Research Fellow (DC2)

  • 2024/08 - 2025/01
    Harvard Medical School / Massachusetts General Hospital　Department of Neurology　Visiting PhD Scholar

Committee Memberships 1

  • Interdisciplinary Information Sciences　Editorial Board Member

    2026/07 - Present

Research Interests 9

  • Brain4AI (Neuroscience for AI)

  • AI4Brain (AI for Neuroscience)

  • Cog4AI (Cognitive Science for AI)

  • AI4Cog (AI for Cognitive Science)

  • EEG Decoding

  • Large Language Models

  • Electroencephalography (EEG)

  • Cognitive Neuroscience

  • Self-Initiated Attention

Research Areas 2

  • Informatics / Intelligent informatics /

  • Life sciences / Cognitive neuroscience /

Awards 7

  1. Silver Medal, ROGII - Wellbore Geology Prediction (89/6125 teams)

    2026/08　Kaggle

  2. Bronze Medal, CSIRO Image2Biomass Prediction (355/3805 teams)

    2026/01　Kaggle

  3. Bronze Medal, Santa 2024: The Perplexity Permutation Puzzle (148/1514 teams)

    2025/01　Kaggle

  4. Best Presentation Award, 32nd Doctoral Student Presentation

    2024/12　Graduate School of Information Sciences, Tohoku University

  5. Student Travel Award

    2023/08　European Conference on Visual Perception (ECVP)

  6. Scholarship for International Students (Apr 2021 – Mar 2023)

    2021/04　Kamei Memorial Foundation

  7. Undergraduate Entrance Scholarship

    2016/09　Tongji University

Show all ︎Show 5

Papers 8

  1. TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting Peer-reviewed

    Lingyu Jiang, Lingyu Xu, Peiran Li, Dengzhe Hou, Qianwen Ge, Dingyi Zhuang, Shuo Xing, Wenjing Chen, Xiangbo Gao, Ting-Hsuan Chen, Xueying Zhan, Xin Zhang, Ziming Zhang, Zhengzhong Tu, Michael Zielewski, Kazunori Yamada, Fangzhou Lin

    Transactions on Machine Learning Research　2026/08

  2. A compact Kolmogorov–Arnold network mixer for long-term time series forecasting Peer-reviewed

    Lingyu Jiang, Dengzhe Hou, Yuping Wang, Yao Su, Shuo Xing, Wenjing Chen, Xin Zhang, Zhengzhong Tu, Ziming Zhang, Fangzhou Lin, Michael Zielewski, Kazunori Yamada

    Scientific Reports　2026/07

    DOI： 10.1038/s41598-026-59667-5 　

  3. Self-Evolving Agent Engineering for Healthcare: Methodologies and Applications

    Dengzhe Hou, Zihao Wu, Yuwen Zeng, Lingyu Jiang, Fangzhou Lin, Kazunori Yamada

    2026/05/22

    DOI： 10.20944/preprints202605.1547.v1 　

  4. PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning

    Lingyu Jiang, Zirui Li, Shuo Xing, Peiran Li, Tsubasa Takahashi, Dengzhe Hou, Zhengzhong Tu, Kazunori Yamada, Fangzhou Lin

    CoRR　abs/2605.23074　2026/05/21

    DOI： 10.48550/arXiv.2605.23074 　

    More details Close

    The emergence of Large Reasoning Language Models (LRMs) has paved the way for tackling complex reasoning tasks through test-time scaling by generating long-form Chain-of-Thought (CoT) trajectories during inference. Meanwhile, these trajectories often contain explicit reflection markers such as ``wait'', ``but'', and ``alternatively'', signaling hesitation, revision, and the consideration of alternative explorations, respectively. Recent studies on test-time control leverage such markers as lightweight handles for steering reasoning, typically treating them as a single coarse-grained category rather than distinguishing their distinct functional roles. In this paper, we conduct type-wise suppression and fixed-prefix intervention, revealing that reflection markers differ not only in their functional roles but also in when they exert the greatest influence. Specifically, different marker classes affect accuracy and generation length in distinct ways, and marker choices are most consequential before the model settles into a stable reasoning trajectory. Motivated by these findings, we introduce PathCal, a novel training-free decoding controller that calibrates reasoning paths by distinguishing marker types and intervening only at locally uncertain states. At each decoding step, PathCal utilizes the distribution over reflection-markers to estimate local competition between maintaining the current reasoning trajectory and initiating a competing branch, and softly rebalances marker logits when competing-branch evidence becomes excessive. Experiments across six reasoning benchmarks demonstrate that PathCal achieves a better efficiency--performance trade-off, improving or preserving accuracy while reducing generation length, without relying on external verifiers or additional sampling.

  5. Subject-Specific Analysis of Self-Initiated Attention Shifts from EEG with Controlled Internal and External Attention Conditions Peer-reviewed

    Yuwen Zeng, Dengzhe Hou, Zhang Zhang, Sai Sun, Yongsong Huang, Chia-huei Tseng, Satoshi Shioiri

    IEEE International Conference on Systems, Man, and Cybernetics (SMC 2026)　2026/05/18

    DOI： 10.48550/arXiv.2605.18251 　

    More details Close

    Self-initiated attention shifts play a critical role in voluntary behavior but are difficult to study due to the absence of explicit temporal markers. While previous studies have examined their neural correlates, it remains unclear how multi-dimensional electroencephalography (EEG) features contribute to their characterization within an interpretable computational framework. In this study, we build on an experimental paradigm developed in our previous work, which enables controlled comparison between task-constrained self-initiated shifts and externally instructed shifts under identical visual stimulation. Within this setting, we investigate whether preparatory EEG activity can distinguish these two types of attention shifts. We adopt a machine learning-based approach and conduct two complementary analyses: (1) a performance-oriented assessment of frequency-specific topographic patterns, and (2) a model-based feature attribution analysis using SHapley Additive exPlanations (SHAP). These analyses provide a structured view of how spectral features across regions of interest contribute to model behavior. Our results demonstrate reliable within-subject classification performance, indicating that preparatory EEG activity contains subject-specific discriminative information within this paradigm. The analysis shows that higher-frequency bands and frontal regions contribute strongly to model decisions, although such contributions should be interpreted cautiously due to the potential influence of non-neural artifacts in high-frequency EEG signals. Overall, this work highlights the value of interpretable machine learning for analyzing subject-specific EEG signal patterns in a controlled experimental setting, with potential applications in personalized and asynchronous brain-machine interface systems.

  6. Task-constrained self-initiated attention shifts are indexed by frontal-midline theta ramping Peer-reviewed

    Dengzhe Hou, Sai Sun, Yasuhiro Hatori, Chia-huei Tseng, Satoshi Shioiri

    FRONTIERS IN HUMAN NEUROSCIENCE　19　1708257　2025/12

    DOI： 10.3389/FNHUM.2025.1708257 　

  7. Commonality of neuronal coherence for motor skill acquisition and interlimb transfer

    Jun Zhao, Yifan Wang, Dengzhe Hou, Sai Sun, János Négyesi, Hitoshi Inada, Satoshi Shioiri, Ryoichi Nagatomi

    Scientific Reports　2025/07/19

    DOI： 10.1038/s41598-025-11943-6 　

  8. EEG activity over ipsilateral and contralateral M1 during simple and complex hand tasks: variations with motor learning Peer-reviewed

    Jun Zhao, Yifan Wang, Dengzhe Hou, János Négyesi, De-Lai Qiu, Ryoichi Nagatomi

    FRONTIERS IN NEUROSCIENCE　19　1681250　2025

    DOI： 10.3389/FNINS.2025.1681250 　

Show all ︎Show first 5

Misc. 10

  1. S1CogBench: What System One Decision Models Can and Cannot Do on Cognitive Experiments

    Dengzhe Hou, Kazunori D. Yamada

    arXiv preprint　arXiv:2611.00911　2026/10/31

    DOI： 10.48550/arXiv.2611.00911 　

  2. Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training

    Binwen Tan, Jingchao Wang, Dengzhe Hou, Lingyu Jiang, Zeyuan Wu, Yunhan Shen, Fangzhou Lin, Kazunori Yamada, Atsushi Koike

    CoRR　abs/2608.08224　2026/08

    DOI： 10.48550/arXiv.2608.08224 　

  3. CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models

    Dengzhe Hou, Lingyu Jiang, Fangzhou Lin, Kazunori D. Yamada

    CoRR　abs/2607.24999　2026/07

    DOI： 10.48550/arXiv.2607.24999 　

  4. CogEEGAgent: Toward Autonomous Cognitive EEG Analysis with Grounded Execution and Selection-Aware Verification

    Dengzhe Hou, Lingyu Jiang, Fangzhou Lin, Kazunori D. Yamada

    CoRR　abs/2607.25045　2026/07

    DOI： 10.48550/arXiv.2607.25045 　

  5. Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability

    Dengzhe Hou, Zihao Wu, Lingyu Jiang, Zirui Li, Fangzhou Lin, Kazunori D. Yamada

    CoRR　abs/2605.07212　2026/05/08

    DOI： 10.48550/arXiv.2605.07212 　

    More details Close

    Electroencephalography (EEG) is a cornerstone of brain-computer interfaces and clinical neuroscience, yet deep learning models are typically trained and evaluated under a single, unreported preprocessing pipeline. We formalize preprocessing choices as a counterfactual intervention space and show that EEG predictions are surprisingly unstable under this space: across six datasets spanning four paradigms, up to 42% of trial-level predictions flip when only the preprocessing changes, a variability that standard uncertainty methods do not explicitly quantify because they condition on a fixed preprocessing pipeline. We provide three tools to make this instability measurable, decomposable, and reducible. First, a Walsh-Hadamard decomposition of the 2^7 pipeline space reveals that sensitivity is near-additive in practice under the binary intervention design, enabling efficient step-by-step optimization. Second, we introduce Preprocessing Uncertainty (PU), a per-trial diagnostic that captures a dimension of instability complementary to model-based confidence. Third, we study Normalized Adaptive PGI (NA-PGI), a graph-structured regularizer that exploits the compositional structure of preprocessing interventions as one mitigation strategy with clear scope conditions.

  6. Physics-Aware Video Instance Removal Benchmark

    Zirui Li, Xinghao Chen, Lingyu Jiang, Dengzhe Hou, Fangzhou Lin, Kazunori Yamada, Xiangbo Gao, Zhengzhong Tu

    CVPR 2026 Workshop on Video Generation and Beyond Evaluation (VGBE)　2026/04/07

    DOI： 10.48550/arXiv.2604.05898 　

    More details Close

    Video Instance Removal (VIR) requires removing target objects while maintaining background integrity and physical consistency, such as specular reflections and illumination interactions. Despite advancements in text-guided editing, current benchmarks primarily assess visual plausibility, often overlooking the physical causalities, such as lingering shadows, triggered by object removal. We introduce the Physics-Aware Video Instance Removal (PVIR) benchmark, featuring 95 high-quality videos annotated with instance-accurate masks and removal prompts. PVIR is partitioned into Simple and Hard subsets, the latter explicitly targeting complex physical interactions. We evaluate four representative methods, PISCO-Removal, UniVideo, DiffuEraser, and CoCoCo, using a decoupled human evaluation protocol across three dimensions to isolate semantic, visual, and spatial failures: instruction following, rendering quality, and edit exclusivity. Our results show that PISCO-Removal and UniVideo achieve state-of-the-art performance, while DiffuEraser frequently introduces blurring artifacts and CoCoCo struggles significantly with instruction following. The persistent performance drop on the Hard subset highlights the ongoing challenge of recovering complex physical side effects.

  7. Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work

    Zihao Wu, Shu Xu, Boyu Chen, Shuo Wan, Yu Li, Wei Ruan, Yuxuan Lyu, Shuo Li, Dajiang Zhu, Tianming Liu, Dengzhe Hou, Lu Zhao

    CoRR　abs/2604.23674　2026/04

    DOI： 10.48550/arXiv.2604.23674 　

  8. WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models

    Dengzhe Hou, Lingyu Jiang, Deng Li, Zirui Li, Fangzhou Lin, Kazunori D Yamada

    arXiv preprint　arXiv:2603.27343　2026/03/28

    DOI： 10.48550/arXiv.2603.27343 　

    More details Close

    Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific cognitive processes. We introduce Working Memory Fidelity-Active Manipulation (WMF-AM), a probe of cumulative state tracking, the ability to maintain and update intermediate results across K sequential operations within a single query, without a scratchpad. Unlike multi-step agent benchmarks that stress task orchestration, WMF-AM isolates within-pass cumulative load by parameterizing depth K. The core probe uses arithmetic accumulation on 28 models from 12 families (0.5B to frontier); a matched non-arithmetic extension (permissions, schedules, inventories) confirms the design generalizes beyond arithmetic. Three construct-isolation ablations confirm that cumulative load, not arithmetic skill or entity tracking, drives difficulty. We release WMF-AM as a lightweight, recalibratable diagnostic for characterizing where models degrade under cumulative load. Code and data can be accessed at https://github.com/dengzhe-hou/WMF-AM

  9. KANMixer: a minimal KAN-centered mixer for long-term time series forecasting

    Lingyu Jiang, Dengzhe Hou, Yuping Wang, Yao Su, Shuo Xing, Wenjing Chen, Xin Zhang, Zhengzhong Tu, Ziming Zhang, Fangzhou Lin, Michael Zielewski, Kazunori D Yamada

    2025/08/03

    More details Close

    Long-term time series forecasting (LTSF) underpins critical applications from energy management to weather prediction, yet achieving reliable multi-step-ahead accuracy remains challenging. Existing LTSF approaches, dominated by MLP- and Transformer-based architectures, either rely on simple linear mappings or introduce increasingly complex hand-crafted inductive biases, raising the question of whether a more expressive and principled nonlinear core could offer a better alternative. Therefore, we investigate whether Kolmogorov-Arnold Networks (KANs), a recently proposed model featuring adaptive basis functions capable of granular modulation of nonlinearities, can improve LTSF performance, and under which design choices they are most effective. Specifically, we propose KANMixer, a minimal KAN-centered architecture consisting of a multi-scale pooling frontend, a KAN-based temporal mixing backbone, and prediction heads. By avoiding heavy auxiliary modules, KANMixer enables a clear assessment of KAN components in LTSF. Across 28 benchmark-horizon settings against nine baselines, KANMixer achieves the best MSE in 16 settings and the best MAE in 11. Furthermore, extensive ablations on three representative datasets show that KAN effectiveness depends strongly on the choice of edge function; B-spline bases outperform Fourier and Wavelet alternatives; the prediction head contributes most to the gains; moderate depth is preferred over deeper unstable stacks; and decomposition priors help MLP but harm KAN. Beyond practical guidance for integrating KAN into LTSF, these results reveal an underexplored dependency between structural priors and backbone nonlinearity: design choices that benefit MLP can degrade KAN.

  10. Machine Learning-Based Analysis of Brain Activity Preceding Self-Initiated Attention Shifts

    金成慧, HOU Dengzhe, 塩入諭

    電子情報通信学会技術研究報告(Web)　125　(291(HIP2025 64-73))　2025

    ISSN： 2432-6380

Show all ︎Show first 5

Presentations 18

  1. AIとニューロテクノロジーのガバナンス Invited

    侯登哲, マイク・ザイルースキ

    第44回日本ロボット学会学術講演会 オープンフォーラム OF7「テクノロジーの質的進化と組織統制」　2026/09/01

  2. From Preprocessing Choices to LLM Agents: Automated and Verifiable Cognitive EEG Analysis International-presentation Invited

    Dengzhe Hou

    The 12th Annual CWRU-Tohoku Data Science in Engineering and Life Sciences Symposium　2026/08/04

  3. Data-Driven Investigation of Brain Mechanisms Underlying Self-Initiated Attention Shifts

    Yuwen Zeng, Dengzhe Hou, Yongsong Huang, Chia-huei Tseng, Satoshi Shioiri

    IEICE Technical Committee on Human Information Processing (HIP)　2025/12/15

  4. Machine Learning-Based Analysis of Brain Activity Preceding Self-Initiated Attention Shifts

    IEICE Technical Committee on Human Information Processing (HIP)　2025/12/15

  5. Machine Learning-Based Analysis of Brain Activity Preceding Self-Initiated Attention Shifts During Free Viewing

    Visual Science Society of Japan 2025 Summer Meeting　2025/09/10

  6. EEG-Based Decoding of Voluntary Attentional Control: Differentiating Self-Initiated Shifts in a Visual Search Paradigm

    Dengzhe Hou, Chia-huei Tseng, Satoshi Shioiri

    EPC & APCV Joint Meeting 2025 (The 17th Asia-Pacific Conference on Vision)　2025/06/20

  7. Task complexity-related neurophysiological dynamics underlying visuomotor skill learning and interlimb transfer International-presentation

    J. Zhao, Y. Wang, D. Hou, S. Sun, J. Négyesi, H. Inada, S. Shioiri, R. Nagatomi

    Society for Neuroscience (SfN) Annual Meeting 2024　2024/10/09

  8. Attention guides reward-based decision-making as measured by SSVEPs International-presentation

    Dengzhe Hou, Sai Sun, Satoshi Shioiri

    Society for Neuroscience (SfN) Annual Meeting 2024　2024/10/09

  9. Exploring Mechanisms of Self-initiated Attention Shifts: Analysis of Theta Wave

    Dengzhe Hou, Sai Sun, Yasuhiro Hatori, Chia-huei Tseng, Satoshi Shioiri

    The 16th Asia-Pacific Conference on Vision (APCV 2024)　2024/07/12

  10. Exploring Mechanisms of Self-initiated Attention Shifts – Analysis of Alpha Wave International-presentation

    Satoshi Shioiri, Dengzhe Hou, Sai Sun, Yasuhiro Hatori, Chia-huei Tseng

    The 16th Asia-Pacific Conference on Vision (APCV 2024)　2024/07/10

  11. Criticality-State-Based Mechanism for Self-Initiated Attention

    Visual Science Society of Japan 2023 Summer Meeting　2023/09/19

  12. Neural activities preceding self-initiated attention International-presentation

    Satoshi Shioiri, Wei Wu, Kazuya Kobayashi, Dengzhe Hou, Shin Ono, Yoshiyuki Sato, Yasuhiro Hatori, Chia-huei Tseng

    European Conference on Visual Perception (ECVP 2023)　2023/08/28

  13. Self-initiation of attentional shift during visual search

    Dengzhe Hou, Sai Sun, Yoshiyuki Sato, Yasuhiro Hatori, Chia-huei Tseng, Satoshi Shioiri

    European Conference on Visual Perception (ECVP 2023)　2023/08/27

  14. Investigation of Self-initiated Attention by EEG Measurements

    Visual Science Society of Japan 2023 Winter Meeting　2023/01/18

  15. Analysis of EEG measures for self-initiated attention

    Visual Science Society of Japan 2022 Summer Meeting　2022/09/05

  16. Critical brain states related with self-initiated attentional shift

    Wei Wu, Kunihiro Kobayashi, Dengzhe Hou, Satoshi Ono, Yoshiyuki Sato, Yasuhiro Hatori, Chia-huei Tseng, Satoshi Shioiri

    Vision Sciences Society (VSS) Annual Meeting 2022　2022/05/15

  17. Searching indexes for self-initiated attention shift

    Visual Science Society of Japan 2022 Winter Meeting　2022/01/19

  18. Investigation of critical brain states to initiate attentional shift

    Wei Wu, Kunihiro Kobayashi, Dengzhe Hou, Satoshi Ono, Yoshiyuki Sato, Yasuhiro Hatori, Satoshi Shioiri

    IEICE Technical Report　2021/10/01

Show all Show first 5

Research Projects 7

  1. The representational format of attentional templates, probed with computational model hierarchies, EEG and eye tracking

    Offer Organization: Japan Society for the Promotion of Science

    System: Grant-in-Aid for Research Activity Start-up

    Institution: Tohoku University

    2026/07 - 2028/03

  2. 自発的脳機能の神経基盤理解

    塩入 諭, 侯 登哲

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業 基盤研究(A)

    Institution: 東北大学

    2024/04 - 2028/03

  3. テクノロジーガバナンスと社会的受容性に基づく課題解決と人材育成

    Offer Organization: 株式会社NTTデータグループ

    Institution: 東北大学未踏スケールデータアナリティクスセンター

    2026/06 - 2027/10

  4. 脳波基盤モデルにおける非脳源アーティファクト依存性の体系的検証

    Offer Organization: 東北大学

    System: 総合知インフォマティクス研究センター研究助成

    Institution: 東北大学総合知インフォマティクス研究センター

    2026/07 - 2027/03

  5. 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

    侯 登哲

    Offer Organization: 東北大学大学院情報科学研究科

    System: 支援経費（学際的研究プロジェクト開拓支援）

    Institution: 東北大学

    2026/04 - 2027/03

  6. Exploring Brain Mechanisms of Self-Initiated Attention: Simultaneous Recording of EEG and Eye Movements

    Offer Organization: Japan Society for the Promotion of Science

    System: Grants-in-Aid for Scientific Research

    Category: Grant-in-Aid for JSPS Fellows

    Institution: Tohoku University

    2025/04/01 - 2026/03/31

  7. 自発的な注意シフトの脳内メカニズムの解明

    侯 登哲

    Offer Organization: 科学技術振興機構（JST）

    System: 次世代研究者挑戦的研究プログラム（SPRING）

    Institution: 東北大学

    2023/04 - 2025/03

Show all Show first 5

Teaching Experience 2

  1. Data Science Training II　Tohoku University

  2. Machine Learning Basics　Tohoku University

Academic Activities 7

  1. International Joint Conference on Neural Networks (IJCNN)

    2026/04/01 - Present

    Activity type: Peer review

  2. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2026)

    2026/04/01 - Present

    Activity type: Peer review

  3. Discover Neuroscience

    2025/01/01 - Present

    Activity type: Peer review

  4. Scientific Reports

    2025/01/01 - Present

    Activity type: Peer review

  5. Journal of NeuroEngineering and Rehabilitation

    2025/01/01 - Present

    Activity type: Peer review

  6. Cognitive Neurodynamics

    2025/01/01 - Present

    Activity type: Peer review

  7. npj Science of Learning

    2025/01/01 - Present

    Activity type: Peer review

Show all Show first 5