Energy-intensive thermochemical processes within chemical manufacturing are a major
contributor to global CO2 emissions. With the increasing push for sustainability, the scientific …

The cost of vision-and-language pre-training has become increasingly prohibitive due to
end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and …

Abstract Vision-Language Pre-training (VLP) has advanced the performance for many vision-
language tasks. However, most existing pre-trained models only excel in either …

Large-scale pre-training and instruction tuning have been successful at creating general-
purpose language models with broad competence. However, building general-purpose …

Low temperature thermal cracking, rutting, moisture damage and fatigue cracking are
popular damages that appear in the asphalt mixture. These problems occur mainly because …

Lung cancer continues to be a malignant tumor with high mortality. Two obstacles interfere
with curative therapy of lung cancer:(i) poor diagnosis at the early stages, as symptoms are …

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised
representation learning method that addresses the fundamental limitations of instance-wise …

Large-scale vision and language representation learning has shown promising
improvements on various vision-language tasks. Most existing methods employ a …

Deep neural networks are known to be annotation-hungry. Numerous efforts have been
devoted to reducing the annotation cost when learning with deep networks. Two prominent …

Subject-driven text-to-image generation models create novel renditions of an input subject
based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties …