Taku Hasegawa
6 papers · 2022–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(23)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Artificial Intelligence
(4)
Machine Learning
(4)
Core AI
(4)
Computer Vision
(3)
Deep Learning
(3)
Learning Types · Deep Learning
(3)
Natural Language Processing
(2)
Applications · Natural Language Processing
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Computer Science
(1)
Analysis
(1)
Application Areas
(1)
Applications · Computer Vision
(1)
Applications · Computer Science
(1)
Keywords
visual question answering
(2)
multimodal learning
(2)
vision-language model
(2)
document understanding
(1)
vision-language alignment
(1)
wavelet transform
(1)
dense retrieval
(1)
semantic space
(1)
text retrieval
(1)
reward model
(1)
foundation model
(1)
image-text retrieval
(1)
self-supervised pretraining
(1)
parameter efficiency
(1)
retrieval-augmented generation
(1)
adapter tuning
(1)
inference cost
(1)
multi-image reasoning
(1)
long context
(1)
position embedding
(1)
Papers
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
ICML 2025
VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
CVPR 2025
Wavelet-based Positional Representation for Long Context
ICLR 2025
DueT: Image-Text Contrastive Transfer Learning with Dual-adapter Tuning
EMNLP 2023
SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images
AAAI 2023
Scene-Text Aware Image and Text Retrieval with Dual-Encoder
ACL 2022