Scholar
Xiaotian Han
Google Scholar ID: 5fHHi24AAAAJ
Research Scientist, OpenAI
Citations & Impact
Citations
485
H-index
11
i10-index
12
Publications
18
Co-authors
20
list available
Publications
Resume (English only)
Academic Achievements
- In 2024, two papers were accepted by NeurIPS 2024: 'DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation' and 'Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model'. Another paper 'InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning' was accepted by the 4th MATH-AI Workshop at NeurIPS 24. Additionally, a paper 'COCO is “ALL’’ You Need for Visual Instruction Fine-tuning' was accepted by ICME 2024.
Research Experience
- Senior Research Scientist at ByteDance Seed; Senior Applied Scientist at Microsoft Azure AI Computer Vision Team.
Education
- M.S. from Duke University; B.S. from University of Science and Technology of China (USTC).
Background
- Currently a Researcher at OpenAI, focusing on multimodal. Formerly a Senior Research Scientist at ByteDance Seed and a Senior Applied Scientist at Microsoft Azure AI Computer Vision Team. Research interests include computer vision, multimodal, reinforcement learning, and deep learning.
