Liqiang Niu
6 papers · 2015–2025 · 4 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Half
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
๐
Trend Setter
Venues
Top co-authors
Research topics
Keywords
contrastive learning
(1)
text-to-image synthesis
(1)
information retrieval
(1)
multimodal learning
(1)
joint learning
(1)
adaptive inference
(1)
large multimodal model
(1)
vision-language model
(1)
multimodal large language model
(1)
distributed representation
(1)
image understanding
(1)
visual token
(1)
word embedding
(1)
multimodal embedding
(1)
hard negative mining
(1)
optical character recognition
(1)
multi-attribute learning
(1)
visual language understanding
(1)
multimodal machine translation
(1)
image-to-text translation
(1)
Papers
AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity
ACL 2025
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning
EMNLP 2025
TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding
EMNLP 2025
Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation
ACL 2024
UMTIT: Unifying Recognition, Translation, and Generation for Multimodal Text Image Translation
COLING 2024
A Unified Framework for Jointly Learning Distributed Representations of Word and Attributes
ACML 2015