activity
20202022
most citedi-Code: An Integrative and Composable Multimodal Learning Framework

4 citations · 9 across the 7 of their papers we have counts for

collaborators

9 papers

cs.CV20221 cited

Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles

Shuquan Ye, Yujia Xie, Dongdong Chen +4

This paper focuses on analyzing and improving the commonsense ability of recent popular vision-language (VL) models. Despite the great success, we observe that existing VL-models s…

cs.CL20222 cited

Empowering Language Models with Knowledge Graph Reasoning for Question Answering

Ziniu Hu, Yichong Xu, Wenhao Yu +5

Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external kn…

cs.CL2022

Task Compass: Scaling Multi-task Pre-training with Task Prefix

Zhuosheng Zhang, Shuohang Wang, Yichong Xu +6

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language mod…

cs.LG20224 cited

i-Code: An Integrative and Composable Multimodal Learning Framework

Ziyi Yang, Yuwei Fang, Chenguang Zhu +17

Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to…

cs.CL2022

Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data

Shuohang Wang, Yichong Xu, Yuwei Fang +5

Retrieval-based methods have been shown to be effective in NLP tasks via introducing external knowledge. However, the indexing and retrieving of large-scale corpora bring considera…

cs.CL20212 cited

Leveraging Knowledge in Multilingual Commonsense Reasoning

Yuwei Fang, Shuohang Wang, Yichong Xu +4

Commonsense reasoning (CSR) requires the model to be equipped with general world knowledge. While CSR is a language-agnostic process, most comprehensive knowledge sources are in fe…