SK
Shuhei Kurita
cs.CVcs.AIcs.CLcs.ROcs.MMcs.LGcond-mat.mtrl-scics.SDeess.ASneuroscience
On Valency
published · living versionsW_msxfpq5v·v1 · currentpublished
DewHand: Direct Metric World-Space Hand Motion Reconstruction from Egocentric Videos
with Naru Suzuki, Satoshi Ikehata, Takehiko Ohkawa, Yoichi Sato
1 version
Preprints & journals
48 papers in the corpus · 2018–2026DewHand: Direct Metric World-Space Hand Motion Reconstruction from Egocentric Videos2610.29936v1 · Naru Suzuki, Satoshi Ikehata, Takehiko Ohkawa et al.2026 · 0 citationsarXivon Valency
Rendering-Free Lookahead for Question-Guided Active Vision2610.11039v1 · Koya Sakamoto, Daichi Azuma, Shuhei Kurita et al.2026 · 0 citationsarXiv
Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse2609.33707v1 · Futa Waseda, Shuhei Kurita, Isao Echizen2026 · 0 citationsarXiv
CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels2608.30342v1 · Jirong Li, Satoshi Ikehata, Shuhei Kurita et al.2026 · 0 citationsarXiv
Synth-JDoc: Synthesizing a Japanese Document Image Dataset for OCR with Diverse Layouts and Embedded Images2608.28248v1 · Keito Sasagawa, Shuhei Kurita, Daisuke Kawahara2026 · 0 citationsarXiv
LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension2607.02096v1 · Shunya Kato, Taiki Miyanishi, Shuhei Kurita et al.2026 · 0 citationsarXiv
LLM-Guided Test-Time Discovery of Quantum-Chemical Approximation Algorithms2606.20729v1 · Masaya Hagai, Yuta Suzuki, Tomoya Murata et al.2026 · 0 citationsarXiv
Neuron Level Analysis of Large Language Model in Legal Domain Reasoning2606.15884v1 · Eri Onami, Youmi Ma, Shuhei Kurita et al.2026 · 0 citationsarXiv
NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation2606.13494v1 · Daichi Azuma, Taiki Miyanishi, Koya Sakamoto et al.2026 · 0 citationsarXiv
HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers2606.01132v2 · Issa Sugiura, Shuhei Kurita, Yusuke Oda et al.2026 · 0 citationsarXiv
E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes2604.17969v3 · Koya Sakamoto, Taiki Miyanishi, Daichi Azuma et al.2026 · 1 citationarXiv
ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning2604.08050v1 · Daichi Yashima, Shuhei Kurita, Yusuke Oda et al.2026 · 0 citationsarXiv
Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models2604.02048v2 · Issa Sugiura, Keito Sasagawa, Keisuke Nakao et al.2026 · 0 citationsarXiv
JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation2604.00909v2 · Issa Sugiura, Koki Maeda, Shuhei Kurita et al.2026 · 0 citationsarXiv
Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting2603.29943v2 · Fumihiko Tsuchiya, Taiki Miyanishi, Shunsuke Yasuki et al.2026 · 0 citationsarXiv
HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching2603.27281v1 · Daichi Yashima, Koki Seno, Shuhei Kurita et al.2026 · 0 citationsarXiv
PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models2603.16958v1 · Hisayuki Yokomizo, Taiki Miyanishi, Yan Gang et al.2026 · 0 citationsarXiv
From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution2603.01113v3 · Kanata Suzuki, Kazuki Hori, Haruka Miyoshi et al.2026 · 0 citationsarXiv
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding2602.16412v2 · Daichi Yashima, Shuhei Kurita, Yusuke Oda et al.2026 · 0 citationsarXiv
Evaluating Multimodal Large Language Models on Vertically Written Japanese Text2511.15059v1 · Keito Sasagawa, Shuhei Kurita, Daisuke Kawahara2025 · 3 citationsarXiv
STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models2510.22571v1 · Mahiro Ukai, Shuhei Kurita, Nakamasa Inoue2025 · 0 citationsarXiv
WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models2510.22276v4 · Issa Sugiura, Shuhei Kurita, Yusuke Oda et al.2025 · 0 citationsarXiv
Referring Expression Comprehension for Small Objects2510.03701v1 · Kanoko Goto, Takumi Hirose, Mahiro Ukai et al.2025 · 0 citationsarXiv
Developing Vision-Language-Action Model from Egocentric Videos2509.21986v1 · Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura et al.2025 · 0 citationsarXiv
Llama-Mimi: Exploring the Limits of Flattened Speech Language Modeling2509.14882v2 · Issa Sugiura, Shuhei Kurita, Yusuke Oda et al.2025 · 0 citationsarXiv
GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields2506.23352v1 · Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue et al.2025 · 1 citationarXiv
Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs2506.19923v5 · Kaito Baba, Chaoran Liu, Shuhei Kurita et al.2025 · 0 citationsarXiv
Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision2506.03605v1 · Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura et al.2025 · 2 citationsarXiv
LegalViz: Legal Text Visualization by Text To Diagram Generation2502.06147v2 · Eri Onami, Taiki Miyanishi, Koki Maeda et al.2025 · 5 citationsarXiv
Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model2410.22736v1 · Keito Sasagawa, Koki Maeda, Issa Sugiura et al.2024 · 0 citationsarXiv
AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering2407.19410v1 · Mahiro Ukai, Shuhei Kurita, Atsushi Hashimoto et al.2024 · 1 citationarXiv
Answerability Fields: Answerable Location Estimation via Diffusion Models2407.18497v1 · Daichi Azuma, Taiki Miyanishi, Shuhei Kurita et al.2024 · 1 citationarXiv
LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs2407.03963v2 · LLM-jp: Akiko Aizawa, Eiji Aramaki, Bowen Chen et al.2024 · 5 citationsarXiv
CityNav: A Large-Scale Dataset for Real-World Aerial Navigation2406.14240v3 · Jungdae Lee, Taiki Miyanishi, Shuhei Kurita et al.2024 · 11 citationsarXiv
Map-based Modular Approach for Zero-shot Embodied Question Answering2405.16559v2 · Koya Sakamoto, Daichi Azuma, Taiki Miyanishi et al.2024 · 5 citationsarXiv
Text-driven Affordance Learning from Egocentric Vision2404.02523v1 · Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura et al.2024 · 6 citationsarXiv
JDocQA: Japanese Document Question Answering Dataset for Generative Language Models2403.19454v1 · Eri Onami, Shuhei Kurita, Taiki Miyanishi et al.2024 · 4 citationsarXiv
Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction2402.17969v1 · Koki Maeda, Shuhei Kurita, Taiki Miyanishi et al.2024 · 0 citationsarXiv
SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition2401.09759v2 · Hao Wang, Shuhei Kurita, Shuichiro Shimizu et al.2024 · 4 citationsarXiv
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data2310.18773v1 · Taiki Miyanishi, Fumiya Kitamori, Shuhei Kurita et al.2023 · 2 citationsarXiv
RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D2308.12035v2 · Shuhei Kurita, Naoki Katsura, Eri Onami2023 · 14 citationsarXiv
Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans2305.13876v3 · Taiki Miyanishi, Daichi Azuma, Shuhei Kurita et al.2023 · 6 citationsarXiv
Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows2209.05840v1 · Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura et al.2022 · 6 citationsarXiv
ScanQA: 3D Question Answering for Spatial Scene Understanding2112.10482v3 · Daichi Azuma, Taiki Miyanishi, Shuhei Kurita et al.2021 · 197 citationsarXiv
Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule2009.07783v3 · Shuhei Kurita, Kyunghyun Cho2020 · 7 citationsarXiv
Reconstructing neuronal circuitry from parallel spike trains.31578320 · Kobayashi, Ryota, Kurita, Shuhei, Kurth, Anno et al.2020 · 146 citationsNature communications. 2019;10(1):4468
Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies1906.01239v1 · Shuhei Kurita, Anders S\ogaard2019 · 25 citationsarXiv
Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis1806.00971v2 · Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi2018 · 14 citationsarXiv
Career total: 76 works. 48 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.