📑 Research Projects

• 

  Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs

  Xingyu Fu, Siyi Liu, Yinuo Xu, Pan Lu, Guangqiuse Hu, Tianbo Yang, Taran Anantasagar, Christopher Shen, Yikai Mao, Yuanzhe Liu, Keyush Shah, Chung Un Lee, Yejin Choi, James Zou, Dan Roth*, Chris Callison-Burch*

  Arxiv 2025 Sep

  [paper] [website] [code] [dataset] [twitter]

• 

  ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

  Xingyu Fu, Minqian Liu, Zhengyuan Yang, John Corring, Yijuan Lu, Jianwei Yang, Dan Roth, Dinei Florencio, Cha Zhang

  ICML 2025

  [paper] [website] [code] [dataset] [twitter]



• 

  Science-T2I: Addressing Scientific Illusions in Image Synthesis

  Jialuo Li, Wenhao Chai, Xingyu Fu, Haiyang Xu, Saining Xie

  CVPR 2025

  [paper] [website] [code] [dataset]



• 

  MUIRBENCH: A Comprehensive Benchmark for Robust Multi-image Understanding

  Fei Wang*, Xingyu Fu*, James Y. Huang, Zekun Li, Qin Liu, Xiaogeng Liu, Mingyu Derek Ma, Nan Xu, Wenxuan Zhou, Kai Zhang, Tianyi Lorena Yan, Wenjie Jacky Mo, Hsiang-Hui Liu, Pan Lu, Chunyuan Li, Chaowei Xiao, Kai-Wei Chang, Dan Roth, Sheng Zhang, Hoifung Poon, Muhao Chen

  ICLR 2025

  [paper] [website] [code] [dataset] [twitter]



• 

  Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models

  Yushi Hu*, Weijia Shi*, Xingyu Fu, Dan Roth, Mari Ostendorf, Luke Zettlemoyer, Noah A Smith, Ranjay Krishna

  NeurIPS 2024

  [paper] [website] [code] [twitter]



• 

  Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?

  Xingyu Fu, Muyu He, Yujie Lu, William Yang Wang, Dan Roth

  COLM 2024

  [paper] [website] [code] [dataset] [twitter]



• 

  BLINK: Multimodal Large Language Models Can See but Not Perceive

  Xingyu Fu*, Yushi Hu*, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin, Dan Roth, Noah A. Smith, Wei-Chiu Ma†, Ranjay Krishna†

  ECCV 2024, Spotlight of cVinW@CVPR 2024, 36K total downloads.

  [paper] [website] [code] [dataset] [eval] [twitter] [ Paper of the day]



• 

  Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?

  Bangzheng Li, Ben Zhou, Fei Wang, Xingyu Fu, Dan Roth, Muhao Chen

  NAACL. 2024.

  [paper] [website] [code] [dataset]



• 

  ImagenHub: Standardizing the evaluation of conditional image generation models

  Max Ku, Tianle Li, Kai Zhang, Yujie Lu, Xingyu Fu, Wenwen Zhuang, Wenhu Chen

  ICLR. 2024.

  [paper] [website] [code] [dataset] [visualization]




• 

  Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge

  Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

  ACL findings. 2023.

  [paper] [website] [code]



• 

  Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering

  Xingyu Fu, Ben Zhou, Sihao Chen, Mark Yatskar, Dan Roth

  Arxiv. 2023.

  [paper]



• 

  There's a Time and Place for Reasoning Beyond the Image

  Xingyu Fu, Ben Zhou, Ishaan Chandratreya, Carl Vondrick, Dan Roth

  ACL (Oral). 2022.

  [paper] [code]



• 

  Design Challenges in Low-resource Cross-lingual Entity Linking

  Xingyu Fu*, Weijia Shi*, Xiaodong Yu, Zian Zhao, Dan Roth

  EMNLP. 2020.

  [paper] [code]



• 

  Constrained sequence-to-sequence semitic root extraction for enriching word embeddings

  Ahmed El-Kishky*, Xingyu Fu*, Aseel Addawood, Nahil Sobh, Clare Voss, Jiawei Han

  WANLP @ ACL. 2019.

  [paper]