Ziyang Miao
4 papers · 2025–2026 · 3 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 · Bronze
🗺️
Taxonomy Completionist
(15)
👥
Mega-Team · Legion
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(3)
Models
(3)
Computer Vision
(2)
Machine Learning
(2)
Natural Language Processing
(2)
Application Areas
(1)
Applications
(1)
Domain-Specific
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Keywords
vision-language model
(2)
domain adaptation
(1)
temporal reasoning
(1)
question answering
(1)
document parsing
(1)
video understanding
(1)
computational efficiency
(1)
coarse-to-fine strategy
(1)
data synthesis
(1)
video benchmark
(1)
video question answering
(1)
video-language model
(1)
table recognition
(1)
self-supervised fine-tuning
(1)
group relative policy optimization
(1)
fine-tuning data
(1)
text extraction
(1)
question-answer generation
(1)
layout analysis
(1)
large language model
(1)
Papers
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
ACL 2026
TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
CVPR 2026
Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
EMNLP 2025
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
CVPR 2025