Vision systems to see and reason about the compositional nature of visual scenes are
fundamental to understanding our world. The complex relations between objects and their …

We propose a simple pairwise sigmoid loss for image-text pre-training. Unlike standard
contrastive learning with softmax normalization, the sigmoid loss operates solely on image …

We launch EVA-02, a next-generation Transformer-based visual representation pre-trained
to reconstruct strong and robust language-aligned vision features via masked image …

Recent text-to-image diffusion models such as MidJourney and Stable Diffusion threaten to
displace many in the professional artist community. In particular, models can learn to mimic …

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

Abstract Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective
and scalable methods for training transferable vision models using paired image and text …

The exponential growth of large language models (LLMs) has opened up numerous
possibilities for multi-modal AGI systems. However the progress in vision and vision …

Recent studies have shown promising results on utilizing large pre-trained image-language
models for video question answering. While these image-language models can efficiently …

Multimodal learning, which aims to understand and analyze information from multiple
modalities, has achieved substantial progress in the supervised regime in recent years …

Mainstream 3D representation learning approaches are built upon contrastive or generative
modeling pretext tasks, where great improvements in performance on various downstream …