2 citations · 2 across the 2 of their papers we have counts for
4 papers
Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
Andrea Burns, Aaron Sarna, Dilip Krishnan +1
Disentangled visual representations have largely been studied with generative models such as Variational AutoEncoders (VAEs). While prior work has focused on generative methods for…
Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments
Andrea Burns, Deniz Arsan, Sanjna Agrawal +3
In recent years, vision-language research has shifted to study tasks which require more complex reasoning, such as interactive question answering, visual common sense reasoning, an…
Learning to Scale Multilingual Representations for Vision-Language Tasks
Andrea Burns, Donghyun Kim, Derry Wijaya +2
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are a…
Language Features Matter: Effective Language Representations for Vision-Language Tasks
Andrea Burns, Reuben Tan, Kate Saenko +2
Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language m…