Shuhei Kurita
(ja: 栗田修平)
Bio
Shuhei Kurita is an assistant professor in National Institute of Informatics. His research interests include natural language processing/understanding (NLP/NLU) with machine learning approaches, deep reinforcement learning (DRL), neuroscience, and statistical/computational physics. Currently, he has a keen interest in developing models with real world understandings such as the vision-and-language navigation task with a language-generation model and 3D world understanding such as ScanQA dataset.
He obtained a Ph.D. of Informatics (Kyoto University) in March 2019.
Contact: 
News
30, June, 2024
Two papers are accepted to IROS2024!
Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto and Motoaki Kawanabe Answerability Fields: Answerable Location Estimation via Diffusion Models, IROS 2024.
Koya Sakamoto, Daichi Azuma, Taiki Miyanishi, Shuhei Kurita and Motoaki Kawanabe, Map-based Modular Approach for Zero-shot Embodied Question Answering, IROS 2024.
21, Feb., 2024
Two papers are accepted to LREC-COLING2024!
Eri Onami, Shuhei Kurita, Taiki Miyanishi, Taro Watanabe, JDocQA: Japanese Document Question Answering Dataset for Generative Language Models
Chieko Nishimura, Shuhei Kurita and Yohei Seki, Text360Nav: 360-Degree Image Captioning Dataset for Urban Pedestrians Navigation
8, Oct., 2023
Two papers are accepted to EMNLP2023 findings!
Koki Maeda, Shuhei Kurita, Taiki Miyanishi, Naoaki Okazaki,
Query-based Image Captioning from Multi-context 360° Images
Shunya Kato, Shuhei Kurita, Chenhui Chu, Sadao Kurohashi,
ARKitSceneRefer: Text-based Localization of Small Objects in Diverse Real-World 3D Indoor Scenes
22, Seq., 2023
Our paper is accepted to NeurIPS2023 Datasets and Benchmarks track!
Taiki Miyanishi, Fumiya Kitamori, Shuhei Kurita, Jungdae Lee, Motoaki Kawanabe, Nakamasa Inoue,
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
20, July, 2023
Our paper is accepted to ICCV2023!
RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D
Shuhei Kurita, Naoki Katsura and Eri Onami
Update: [arXiv paper] [code] available!
1, April, 2023
I become a research scientist in the RIKEN-AIP LIAT team, Japan.
1, Feb., 2023
We will obtain JSPS Fund for the Promotion of Joint International Research (Fostering Joint International Research(A)) （科研費 国際共同研究強化（Ａ））from Japan, starting from April, 2023!
10, Oct., 2022
We will make the follwing two presentations at COLING2022 conference!
- Shuhei Kurita, Hiroki Ouchi, Kentaro Inui and Satoshi Sekine Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling.
- Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku and Shinsuke Mori Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows.
Thank you to my co-authors!!
2, Mar., 2022
Our paper is accepted to CVPR2022!
ScanQA: 3D Question Answering for Spatial Scene Understanding
Daichi Azuma(*), Taiki Miyanishi(*), Shuhei Kurita(*), Motoaki Kawanabe.
(*): equally contributed
Thank you to my co-authors!!
1, Mar., 2022
My research grant proporal for JSPS Grant-in-Aid for Young Scientists in Japan is acceped!
26, Aug., 2021
Our paper is accepted to EMNLP2021 Findings!
Co-Teaching Student-Model through Submission Results of Shared Task
Kouta Nakayama, Shuhei Kurita, Akio Kobayashi, Yukino Baba and Satoshi Sekine.
12, Jan., 2021
Our paper at NYU visiting with Prof. Kyunghyun Cho is accepted to ICLR2021!
Shuhei Kurita and Kyunghyun Cho
Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes’ Rule. OpenReview
24, Nov., 2020
I am selected as a JST PRESTO “Trustworthy AI” reseach project member from December!
(~3.5 years, ~40M yens.)
I will delightedly work with many researchers in and out of PRESTO!
9, Jan., 2020
Thank you for Prof. Kyunghyun Cho and many NYU people, I start my co-working with Cho at NYU from this January. If you are at NYU or NY, I’m so happy to work with you. Feel free to reach me!
2, Oct., 2019
Our paper “Reconstructing neuronal circuitry from parallel spike trains” has been published from Nature Communications! Ryota Kobayashi, Shuhei Kurita, Anno Kurth, Katsunori Kitano, Kenji Mizuseki, Markus Diesmann, Barry J. Richmond & Shigeru Shinomoto.
https://www.nature.com/articles/s41467-019-12225-2
14, May, 2019
Our paper “Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies,” (Long) has been accepted to ACL2019!
https://www.aclweb.org/anthology/P19-1232/
1, April, 2019
I received Ph.D. of Informatics from Kyoto University on March 25, 2019! Now I join the Center for Advanced Intelligence Project, RIKEN, Nihombashi, Tokyo with Prof. Satoshi Sekine. I am adapted to JST ACT-I Research Projects Acceleration Phase (2019.4-2021.3).