Is vision good enough for language? Recent advancements in multimodal models primarily
stem from the powerful reasoning abilities of large language models (LLMs). However the …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

Open-vocabulary object detection has benefited greatly from pretrained vision-language
models, but is still limited by the amount of available detection training data. While detection …

Mamba, a recent selective structured state space model, performs excellently on long
sequence modeling tasks. Mamba mitigates the modeling constraints of convolutional …

Contrastive pretraining on image-text pairs from the web is one of the most popular large-
scale pretraining strategies for vision backbones, especially in the context of large …

Recent advances in large-scale pretraining have yielded visual foundation models with
strong capabilities. Not only can recent models generalize to arbitrary images for their …

Activity and property prediction models are the central workhorses in drug discovery and
materials sciences, but currently, they have to be trained or fine-tuned for new tasks. Without …

In this report, we introduce InternVL 1.5, an open-source multimodal large language model
(MLLM) to bridge the capability gap between open-source and proprietary commercial …

This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that
compares favorably to similar models that are 10x larger. As part of arriving at this strong …

General-purpose foundation models have led to recent breakthroughs in artificial
intelligence (AI). In remote sensing, self-supervised learning (SSL) and masked image …