Fuxiao Liu

刘赋骁

Research Scientist at NVIDIA, working on the Nemotron family of foundation models.

Ph.D. from University of Maryland, College Park (May 2025), advised by Abhinav Shrivastava, Yaser Yacoob, Tianyi Zhou, and Furong Huang.

My recent focus is on building customizable, efficient, and open multimodal foundation models.

Selected Publications

NVIDIA
Nemotron
Nano 2 VL

NVIDIA · 2025

NVIDIA Nemotron Nano V2 VL: Efficient Open Vision-Language Foundation Model NEWCore Author

NVIDIA Nemotron Team (incl. Fuxiao Liu)

Project HuggingFace

Nemotron 3
Nano Omni

NVIDIA · 2025

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence NEWCore Author

NVIDIA Nemotron Team (incl. Fuxiao Liu)

Project HuggingFace

Nemotron-H
Mamba ⨯ Transformer

NVIDIA · 2025

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba–Transformer Models NEWCore Author

NVIDIA Nemotron Team (incl. Fuxiao Liu)

Paper Project HuggingFace

ICLR 2025

EAGLE: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Fuxiao Liu*, Min Shi*, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, De-An Huang, Hongxu Yin, Karan Sapra, Yaser Yacoob, Humphrey Shi, Bryan Catanzaro, Andrew Tao, Jan Kautz, Zhiding Yu*, Guilin Liu*

Paper Code BibTeX

ICLR 2024

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Fuxiao Liu*, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, Lijuan Wang

Paper Code BibTeX

CVPR 2024

HallusionBench: You See What You Think? Or You Think What You See?

Fuxiao Liu*, Tianrui Guan*, Xiyang Wu, Ruiqi Xian, Xijun Wang, Zongxia Li, Lichang Chen, Yaser Yacoob, Dinesh Manocha, Tianyi Zhou

Paper Code BibTeX

NAACL 2024

MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning

Fuxiao Liu*, Xiaoyang Wang, Wenlin Yao, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Yaser Yacoob, Dong Yu

Paper Code BibTeX

ICPRAI 2023

DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents

Fuxiao Liu*, Hao Tan, Chris Tensmeyer

Paper Code BibTeX

EACL 2023 · Oral

COVID-VTS: Fact Extraction and Verification on Short Video Platforms

Fuxiao Liu*, Yaser Yacoob, Abhinav Shrivastava

Paper Code BibTeX

EMNLP 2021 · Oral

Visual News: Benchmark and Challenges in News Image Captioning

Fuxiao Liu*, Yinghan Wang, Tianlu Wang, Vicente Ordonez

Paper Code BibTeX

Other Publications

[NAACL 2025] Large language models and causal inference in collaboration: A comprehensive survey

Xiaoyu Liu, Paiheng Xu, Junda Wu, Yuhang Zhou, Fuxiao Liu*, Tianrui Guan, Haoliang Wang, Tong Yu, Julian McAuley, Wei Ai, Furong Huang

[NeurIPS 2024 Workshop] Towards understanding in-context learning with contrastive demonstrations and saliency maps

Fuxiao Liu*, Paiheng Xu, Zongxia Li

[LREC-COLING 2024] From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning, Efficiency and Beyond

Fao Fei, Yuan Yao, Zhuosheng Zhang, Fuxiao Liu*, Ao Zhang, Tat-seng Chua

[ACL 2024] Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences

Xiyao Wang, Yuhang Zhou, Xiaoyu Liu, Hongjin Lu, Yuancheng Xu, Fuxiao Liu*, Mohit Bansal, Furong Huang

[IROS 2025] On the Safety Concerns of Deploying LLMs/VLMs in Robotics: Highlighting the Risks and Vulnerabilities

Xiyang Wu, Ruiqi Xian, Tianrui Guan, Jing Liang, Souradip Chakraborty, Fuxiao Liu*, Brian Sadler, Dinesh Manocha, Amrit Singh Bedi

[IROS 2024] SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition

Xijun Wang*, Ruiqi Xian, Tianrui Guan, Fuxiao Liu*, Dinesh Manocha

[ICMLA 2024] DeepFM-CRISPR: Enhancing CRISPR On-Target Prediction with Deep Learning

Condy Bao, Fuxiao Liu*

[ACL 2025] Mosaic IT: Enhancing Instruction Tuning with Data Mosaics

Ming Li, Pei Chen, Chenguang Wang, Hongyu Zhao, Yijun Liang, Yupeng Hou, Fuxiao Liu*, Tianyi Zhou

[CVPR 2025 Workshop] A Survey of State of the Art Large Vision Language Models: Benchmark Evaluations and Challenges

Zongxia Li, Xiyang Wu, Hongyang Du, Fuxiao Liu*, Huy Nghiem, Guangyao Shi

Service

Conference Reviewer

AISTATS, CVPR, NAACL, ACL, IJCAI, ACMMM

Journal Reviewer

JMIR

About

I'm crazy about basketball since I was a little boy. I love it for its ultimate technical and mentality requirements. No one in the world can become a master without great talent and extensive training. My favorite basketball player is Kobe Bryant, who is noted for his rapid playing style, strong will, and his ambivalent relationship with the sport. I am always immersed in his phenomenal performance in the game.