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

Understanding and reasoning about spatial relationships is crucial for Visual Question
Answering (VQA) and robotics. Vision Language Models (VLMs) have shown impressive …

While deep learning models have become the predominant method for medical image
segmentation, they are typically not capable of generalizing to unseen segmentation tasks …

In-context learning provides a new perspective for multi-task modeling for vision and NLP.
Under this setting the model can perceive tasks from prompts and accomplish them without …

Spatially dense self-supervised learning is a rapidly growing problem domain with
promising applications for unsupervised segmentation and pretraining for dense …

With the rise of large-scale models trained on broad data, in-context learning has become a
new learning paradigm that has demonstrated significant potential in natural language …

Large Language Models like ChatGPT demonstrate a remarkable capacity to learn new
concepts during inference without any fine-tuning. However, visual models trained to detect …

The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models
(VFMs). SAM excels in segmentation tasks across diverse domains, while CLIP is renowned …

In-context segmentation has drawn more attention with the introduction of vision foundation
models. Most existing approaches adopt metric learning or masked image modeling to build …

Existing learning-based solutions to medical image segmentation have two important
shortcomings. First for most new segmentation tasks a new model has to be trained or fine …