[161] MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks25min 2022Q4 XAI ACL
[149] Noise-aware Learning from Web-crawled Image-Text Data for Image CaptioningICCV 25min 2022Q4 kakao
[97] Contrastive Language-Image Pre-Training with Knowledge Graphmultimodal NeurIPS graph 2022Q4 CLIP
[89] Relational Attention: Generalizing Transformers for Graph-Structured Tasksmicrosoft graph 2022Q4 transformer
[71] Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers25min sparse 2022Q4 transformer