68 citations · 278 across the 31 of their papers we have counts for
4 papers · 1 filter
Gated Linear Attention Transformers with Hardware-Efficient Training
Songlin Yang, Bailin Wang, Yikang Shen +2
Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-…
Learning Human Action Recognition Representations Without Real Humans
Howard Zhong, Samarth Mishra, Donghyun Kim +7
Pre-training on massive video datasets has become essential to achieve high action recognition performance on smaller downstream datasets. However, most large-scale video datasets…
LangNav: Language as a Perceptual Representation for Navigation
Bowen Pan, Rameswar Panda, SouYoung Jin +4
We explore the use of language as a perceptual representation for vision-and-language navigation (VLN), with a focus on low-data settings. Our approach uses off-the-shelf vision sy…
Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
Sivan Doveh, Assaf Arbelle, Sivan Harary +9
Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, vis…