Members

Manabu OKUMURA

Professor. Natural language processing, intelligent information presentation, language learning support, text mining

Kotaro FUNAKOSHI

Associate Professor. Natural language processing, multimodal dialogue systems, human-machine interaction

Satoshi KOSUGI

Assistant Professor. Computer vision, image recognition

Nobuko IIYAMA

Administrative Assistant

Dongyuan Li

Specially Appointed Researcher

CAI YUANYUAN

JIARAMANEEPINIT BOONNITHI

PARK JAEEON

XIONG,YE

Multimodal summarization

ZHU, TIANJIAO

Medical Image Analysis, Multimodal Learning, Vision-Language Models

REN KEXIN

SHEN, JIALUN

Multimodal AI, AI Agents

TAN, SHIYIN

Multi-Document Summarization, Graph-based learning, Recommendation

THIRAFI FAZA

WANG, YUSONG

Multimodal Personality Traits Recognition, Mutlimodal Machine Translation

XU YICHENG

MAEKAWA ARU

MYA EI SAN

Low-Resource Machine Translation

OBI, TAKAO

Multimodal Dialogue System, Human-Machine Interaction

SATO TOSHINORI

DUAN, YUTONG

My research focuses on information extraction from materials science literature using large language models. I am currently investigating hallucinations in LLM-based information extraction and methods for their evaluation and mitigation.

HUANG, YIQIAN

My main research interest is training machanism of language models, especially post-training mechanisms towards trustworthy and controllable knowledge manipulation and reasoning behavior for LLMs.

KAWARADA MASAYUKI

LYU, BOXUAN

Machine translation, natural language generation, multimodal

YU, RUNJIA

Intersection of quantitative finance and artificial intelligence

XI XIANGWEN

SASAKI YUTA

Noise-Robust Audio-Visual Speech Recognition Using Lip-Reading Video

ZHU YANJUN

LIN, AILIANG

Semantics, Information Retrieval, Vision-Language Model

MAEDA SHINJI

MAO KEYU

Multimodal Learning, LLM Agents, Causal Inference

DA CUNHA THEODORE MATTHEW PATAWARI

HE, ZIMENG

LLM Agents, Long-term Memory, Persona Consistency, and Reinforcement Learning

ISHIWATA,TAICHI

Slide-aware Presentation ASR

NAKANE RYOSUKE

SENGOKU, YUSEI

Development of a proactive dialogue system that imitates speech-language-hearing therapist

SHINAGAWA KENTARO

SUGIHARA, KOSUKE

Agent-based Semi-Automatic Sign Language Annotation

TOMIZAWA, AKINOJO

Information Retieval, LLM Agents

YAMAUCHI, ISATO

Vision-Language Navigation

ZHU, XINGYU

MLLM-Powered Agent, Vision-Language Model

CHEN GUANGYU

Machine Translation, Efficient MBR Decoding

KAWAKAMI, HARUYA

Simultaneous generation of language and action. I work on externalizing a model's reasoning into a visual workspace to improve long-range and spatial consistency in generation.

NAKAGAWA YU

LLM, RAG, Embedding Model

WU TONG

YAN, YIHAN

Designing AI Agent Interaction Across Private and Shared Spaces in Multi-Party Collaboration

YANG YU HSIANG

MIYAMOTO, KAITO

Information Retrieval

TORIGOE, SOICHIRO

Visual encoder specialized for human interaction