Scholar
Fuxiao Liu
Google Scholar ID: e0P54E4AAAAJ
Research Scientist, NVIDIA
Citations & Impact
Citations
2,395
H-index
14
i10-index
15
Publications
20
Co-authors
17
list available
Publications
Resume (English only)
Academic Achievements
- EAGLE: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders, ICLR 2025.
- Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning, ICLR 2024.
- HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark, CVPR 2024.
- MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning, NAACL 2024.
- DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents, ICPRAI 2023.
- COVID-VTS: Fact Extraction and Verification on Short Video Platforms, EACL 2023.
- Visual News: Benchmark and Challenges in News Image Captioning, EMNLP 2021.
Research Experience
- Spring 2024, NVIDIA ADLR, with Guilin Liu and Zhiding Yu on building Large Multimodal Models.
- Summer 2023, Tencent AI, with Xiaoyang Wang, Jianshu Chen, Kaiqiang Song, Wenlin Yao on Visual Chart Understanding.
- Spring 2023, Microsoft Research, with Linjie Li, Kevin Lin, Jianfeng Wang on Robust Visual Instruction Tuning.
- Summer 2022, Adobe Research, with Chris Tensmeyer, Hao Tan, Ani Nenkova on Visual Document Understanding.
- Spring 2022, UMIACS, with Abhinav Shrivastava on Fact Checking on Short Video.
- Spring 2021, UVa Vislang Lab, with Vicente Ordonez on News Image Captioning.
Education
- Ph.D., University of Maryland, College Park, May 2025; Advisors: Abhinav Shrivastava, Yaser Yacoob, Tianyi Zhou, Furong Huang.
Background
- Research Interests: Building customizable large models that follow humans' intent. Specialization: Computer Vision, Multimodal Learning.
Miscellany
- Personal interests not provided.
