A lightweight framework that gives language models (LMs) a persistent, evolving memory during inference time. Dynamic Cheatsheet (DC) endows black-box language models with the ability to store and ...

By allowing models to actively update their weights during inference, Test-Time Training (TTT) creates a "compressed memory" ...

When major floors are tested by the markets, the greatest gains are often made by those who got in early, as opposed to those ...

Abstract: Dynamic point cloud compression is essential for efficient 3D visual data transmission and storage. To achieve satisfactory coding efficiency, existing learning-based frameworks typically ...

Abstract: Compressive autoencoders (CAEs) play an important role in deep learning-based image compression, but large-scale CAEs are computationally expensive. We propose a framework with three ...

Cross-link density impacts most mechanical properties of rubber, therefore it is necessary to have a method to measure it. The most widely used method is via equilibrium swelling, however, it is time ...