Alert button
Picture for Xingyu Fu

Xingyu Fu

Alert button

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

Nov 16, 2023
Bangzheng Li, Ben Zhou, Fei Wang, Xingyu Fu, Dan Roth, Muhao Chen

Viaarxiv icon

ImagenHub: Standardizing the evaluation of conditional image generation models

Oct 17, 2023
Max Ku, Tianle Li, Kai Zhang, Yujie Lu, Xingyu Fu, Wenwen Zhuang, Wenhu Chen

Figure 1 for ImagenHub: Standardizing the evaluation of conditional image generation models
Figure 2 for ImagenHub: Standardizing the evaluation of conditional image generation models
Figure 3 for ImagenHub: Standardizing the evaluation of conditional image generation models
Figure 4 for ImagenHub: Standardizing the evaluation of conditional image generation models
Viaarxiv icon

Typing on Any Surface: A Deep Learning-based Method for Real-Time Keystroke Detection in Augmented Reality

Aug 31, 2023
Xingyu Fu, Mingze Xi

Figure 1 for Typing on Any Surface: A Deep Learning-based Method for Real-Time Keystroke Detection in Augmented Reality
Figure 2 for Typing on Any Surface: A Deep Learning-based Method for Real-Time Keystroke Detection in Augmented Reality
Figure 3 for Typing on Any Surface: A Deep Learning-based Method for Real-Time Keystroke Detection in Augmented Reality
Figure 4 for Typing on Any Surface: A Deep Learning-based Method for Real-Time Keystroke Detection in Augmented Reality
Viaarxiv icon

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

May 30, 2023
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

Figure 1 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Figure 2 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Figure 3 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Figure 4 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Viaarxiv icon

Interpretable by Design Visual Question Answering

May 24, 2023
Xingyu Fu, Ben Zhou, Sihao Chen, Mark Yatskar, Dan Roth

Figure 1 for Interpretable by Design Visual Question Answering
Figure 2 for Interpretable by Design Visual Question Answering
Figure 3 for Interpretable by Design Visual Question Answering
Figure 4 for Interpretable by Design Visual Question Answering
Viaarxiv icon

There is a Time and Place for Reasoning Beyond the Image

Mar 28, 2022
Xingyu Fu, Ben Zhou, Ishaan Preetam Chandratreya, Carl Vondrick, Dan Roth

Figure 1 for There is a Time and Place for Reasoning Beyond the Image
Figure 2 for There is a Time and Place for Reasoning Beyond the Image
Figure 3 for There is a Time and Place for Reasoning Beyond the Image
Figure 4 for There is a Time and Place for Reasoning Beyond the Image
Viaarxiv icon

An FEA surrogate model with Boundary Oriented Graph Embedding approach

Aug 30, 2021
Xingyu Fu, Fengfeng Zhou, Dheeraj Peddireddy, Zhengyang Kang, Martin Byung-Guk Jun, Vaneet Aggarwal

Figure 1 for An FEA surrogate model with Boundary Oriented Graph Embedding approach
Figure 2 for An FEA surrogate model with Boundary Oriented Graph Embedding approach
Figure 3 for An FEA surrogate model with Boundary Oriented Graph Embedding approach
Figure 4 for An FEA surrogate model with Boundary Oriented Graph Embedding approach
Viaarxiv icon

SRQA: Synthetic Reader for Factoid Question Answering

Sep 02, 2020
Jiuniu Wang, Wenjia Xu, Xingyu Fu, Yang Wei, Li Jin, Ziyan Chen, Guangluan Xu, Yirong Wu

Figure 1 for SRQA: Synthetic Reader for Factoid Question Answering
Figure 2 for SRQA: Synthetic Reader for Factoid Question Answering
Figure 3 for SRQA: Synthetic Reader for Factoid Question Answering
Figure 4 for SRQA: Synthetic Reader for Factoid Question Answering
Viaarxiv icon