3 citations · 5 across the 3 of their papers we have counts for
4 papers
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
Jing Ding, Ziqiao Ma, Jiayuan Mao +2
We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence. We hypothesize a metonymic grounding mechani…
Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models
Yue Zhang, Ziqiao Ma, Jialu Li +6
Vision-and-Language Navigation (VLN) has gained increasing attention over recent years and many approaches have emerged to advance their development. The remarkable achievements of…
GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning
Guangyue Xu, Joyce Chai, Parisa Kordjamshidi
Pre-trained vision-language models (VLMs) have achieved promising success in many fields, especially with prompt learning paradigm. In this work, we propose GIP-COL (Graph-Injected…
MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition
Guangyue Xu, Parisa Kordjamshidi, Joyce Chai
Humans have the ability to learn novel compositional concepts by recalling and generalizing primitive concepts acquired from past experiences. Inspired by this observation, in this…