activity
20192024
most citedPaLI: A Jointly-Scaled Multilingual Language-Image Model

196 citations · 704 across the 16 of their papers we have counts for

collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2024★ 13 cited

PaliGemma: A versatile 3B VLM for transfer

Lucas Beyer, Andreas Steiner, André Susano Pinto +32

PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly know…

cs.CV2024★ 3 cited

Routers in Vision Mixture of Experts: An Empirical Study

Tianlin Liu, Mathieu Blondel, Carlos Riquelme +1

Mixture-of-Experts (MoE) models are a promising way to scale up model capacity without significantly increasing computational cost. A key component of MoEs is the router, which dec…

cs.CV2023★ 16 cited

Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

Mostafa Dehghani, Basil Mustafa, Josip Djolonga +12

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challeng…

cs.CV2023★ 118 cited

Scaling Vision Transformers to 22 Billion Parameters

Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…

cs.CV2022★ 196 cited

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Xi Chen, Xiao Wang, Soravit Changpinyo +26

Effective scaling and a flexible task interface enable large language models to excel at many tasks. We present PaLI (Pathways Language and Image model), a model that extends this…

cs.CV2022★ 72 cited

Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts

Basil Mustafa, Carlos Riquelme, Joan Puigcerver +2

Large sparsely-activated models have obtained excellent performance in multiple domains. However, such models are typically trained on a single modality at a time. We present the L…