Xinyu Wei
7 papers · 2020–2026 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(27)
Top co-authors
Research topics
Artificial Intelligence
(4)
Computer Vision
(4)
Core AI
(4)
Deep Learning
(3)
Machine Learning
(3)
Analysis
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Processing
(2)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Keywords
multimodal large language model
(3)
image generation
(2)
instruction tuning
(2)
mathematical reasoning
(1)
knowledge distillation
(1)
chain-of-thought reasoning
(1)
multimodal learning
(1)
image editing
(1)
object tracking
(1)
continual adaptation
(1)
synthetic data
(1)
vision-language model
(1)
parameter quantization
(1)
fine-grained understanding
(1)
visual prompting
(1)
diffusion transformer
(1)
trajectory reconstruction
(1)
sports analytics
(1)
broadcast video
(1)
camera calibration
(1)
Papers
MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
CVPR 2026
Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
ICLR 2025
Event2Tracking: Reconstructing Multi-Agent Soccer Trajectories Using Long-Term Multimodal Context
AAAI 2025
MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
ICLR 2025
PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions
ICLR 2025
Cloud-Device Collaborative Learning for Multimodal Large Language Models
CVPR 2024
End-to-End Camera Calibration for Broadcast Videos
CVPR 2020