Koki Maeda

16 papers A* 1B 1Journal 9Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Autonomous Decentralized TRP Group Selection Method to Maximize System Throughput in Downlink Distributed MIMO with Overlapped TRP Group Configuration.
IEICE Trans. Commun.
Yuta Yagi, Koki Maeda, Takanori Hara, Satoshi Suyama, Satoshi Nagata, Kenichi Higuchi
2026 J jnl
From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models.
CoRR
Masanari Oi, Koki Maeda, Ryuto Koike, Daisuke Oba, Nakamasa Inoue, Naoaki Okazaki
2026 J jnl
JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding.
CoRR
Koki Maeda, Naoaki Okazaki
2025 J jnl
Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models.
CoRR
Youmi Ma, Sakae Mizuki, Kazuki Fujii, Taishi Nakamura, Masanari Ohi, Hinari Shimada, Taihei Shiotani, Koshiro Saito, Koki Maeda, Kakeru Hattori, Takumi Okamoto, Shigeki Ishida, Rio Yokota, Hiroya Takamura, Naoaki Okazaki
2025 — conf
Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model.
NAACL (System Demonstrations)
Keito Sasagawa, Koki Maeda, Issa Sugiura, Shuhei Kurita, Naoaki Okazaki, Daisuke Kawahara
2025 — conf
LegalViz: Legal Text Visualization by Text To Diagram Generation.
NAACL (Long Papers)
Eri Onami, Taiki Miyanishi, Koki Maeda, Shuhei Kurita
2025 J jnl
LegalViz: Legal Text Visualization by Text To Diagram Generation.
CoRR
Eri Onami, Taiki Miyanishi, Koki Maeda, Shuhei Kurita
2024 — conf
Autonomous Decentralized TRP Group Selection to Maximize System Throughput in Downlink Distributed MIMO System.
VTC Fall
Koki Maeda, Takanori Hara, Satoshi Suyama, Satoshi Nagata, Kenichi Higuchi
2024 — conf
COM Kitchens: An Unedited Overhead-View Video Dataset as a Vision-Language Benchmark.
ECCV (65)
Koki Maeda, Tosho Hirasawa, Atsushi Hashimoto, Jun Harashima, Leszek Rybicki, Yusuke Fukasawa, Yoshitaka Ushiku
2024 J jnl
COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark.
CoRR
Koki Maeda, Tosho Hirasawa, Atsushi Hashimoto, Jun Harashima, Leszek Rybicki, Yusuke Fukasawa, Yoshitaka Ushiku
2024 J jnl
Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model.
CoRR
Keito Sasagawa, Koki Maeda, Issa Sugiura, Shuhei Kurita, Naoaki Okazaki, Daisuke Kawahara
2024 J jnl
Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction.
CoRR
Koki Maeda, Shuhei Kurita, Taiki Miyanishi, Naoaki Okazaki
2024 J jnl
Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs.
CoRR
Koshiro Saito, Sakae Mizuki, Masanari Ohi, Taishi Nakamura, Taihei Shiotani, Koki Maeda, Youmi Ma, Kakeru Hattori, Kazuki Fujii, Takumi Okamoto, Shigeki Ishida, Hiroya Takamura, Rio Yokota, Naoaki Okazaki
2023 A* conf
DueT: Image-Text Contrastive Transfer Learning with Dual-adapter Tuning.
EMNLP
Taku Hasegawa, Kyosuke Nishida, Koki Maeda, Kuniko Saito
2023 — conf
Query-based Image Captioning from Multi-context 360cdegree Images.
EMNLP (Findings)
Koki Maeda, Shuhei Kurita, Taiki Miyanishi, Naoaki Okazaki
2022 B conf
IMPARA: Impact-Based Metric for GEC Using Parallel Data.
COLING
Koki Maeda, Masahiro Kaneko, Naoaki Okazaki