153 citations · 171 across the 4 of their papers we have counts for
6 papers
DisinfoMeme: A Multimodal Dataset for Detecting Meme Intentionally Spreading Out Disinformation
Jingnong Qu, Liunian Harold Li, Jieyu Zhao +2
Disinformation has become a serious problem on social media. In particular, given their short format, visual attraction, and humorous nature, memes have a significant advantage in…
On the Paradox of Learning to Reason from Data
Honghua Zhang, Liunian Harold Li, Tao Meng +2
Logical reasoning is needed in a wide range of NLP tasks. Can a BERT model be trained end-to-end to solve logical reasoning problems presented in natural language? We attempt to an…
How Much Can CLIP Benefit Vision-and-Language Tasks?
Sheng Shen, Liunian Harold Li, Hao Tan +5
Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to pe…
Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
Liunian Harold Li, Haoxuan You, Zhecan Wang +3
Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel imag…
VisualBERT: A Simple and Performant Baseline for Vision and Language
Liunian Harold Li, Mark Yatskar, Da Yin +2
We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly…
Efficient Contextual Representation Learning Without Softmax Layer
Liunian Harold Li, Patrick H. Chen, Cho-Jui Hsieh +1
Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the l…