Gangyan Zeng
6 papers · 2025–2026 · 2 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 · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(20)
🐣
Hot Topic Early Bird
⭐
Rising Star
(6)
Top co-authors
Research topics
Artificial Intelligence
(5)
Computer Vision
(4)
Core AI
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Applications
(3)
Learning Types · Deep Learning
(3)
Domain-Specific
(2)
Models
(2)
Machine Learning
(1)
Analysis
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Processing
(1)
Resources & Methods
(1)
Keywords
contrastive learning
(1)
zero-shot learning
(1)
visual question answering
(1)
attention mechanism
(1)
chain-of-thought reasoning
(1)
information retrieval
(1)
multimodal learning
(1)
document understanding
(1)
document parsing
(1)
image editing
(1)
cross-modal retrieval
(1)
parameter-efficient transfer learning
(1)
cross-modal representation
(1)
synthetic data generation
(1)
benchmark dataset
(1)
vision-language model
(1)
multimodal large language model
(1)
video question answering
(1)
scene synthesis
(1)
visual document understanding
(1)
Papers
MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation
CVPR 2026
Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
CVPR 2026
Towards Training-free Scene Text Editing
CVPR 2026
CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
CVPR 2025
Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
CVPR 2025
Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues
AAAI 2025