Firehose

This paper develops a framework called DeformSmith that generates deformable assets for robots, such as 3D models with realistic physical behavior, to simulate and interact with in the real world. Practitioners in robotics and computer vision might care about DeformSmith because it can help create more realistic and interactive simulations of deformable objects.

This paper develops a new method for creating robust visual representations in images, which can better handle noisy or distorted data, and improves the performance of downstream tasks such as image classification. Practitioners might care about this approach as it can enhance the robustness of image recognition systems in real-world applications.

This paper develops a method to compress a cell segmentation model called Cellpose-SAM to reduce its size, making it more suitable for deployment on low-power devices in laboratories. Practitioners who work with stem cell microscopy may care about this research because it helps ensure that compressed models still produce accurate results, which is crucial for applications where model accuracy is critical.