Update 2025.11.27: Major refactoring into modular architecture (Module A/B/C plus unified interface) with comprehensive benchmark suite. Update 2025.06.25: Added PyAMGX support with improved ...
Abstract: Efficient compression of sparse point cloud geometry remains a critical challenge in 3D content processing, particularly for low-rate scenarios where conventional codecs struggle to maintain ...
Important Note: This repository implements SVG-T2I, a text-to-image diffusion framework that performs visual generation directly in Visual Foundation Model (VFM) representation space, rather than ...
Abstract: Learning-based point cloud compression has achieved great success in Rate-Distortion (RD) efficiency. Existing methods usually utilize Variational AutoEncoder (VAE) network, which might lead ...
Researchers at DeepSeek on Monday released a new experimental model called V3.2-exp, designed to have dramatically lower inference costs when used in long-context operations. DeepSeek announced the ...
Sparse autoencoders are central tools in analyzing how large language models function internally. Translating complex internal states into interpretable components allows researchers to break down ...
Sparse autoencoders (SAEs) are an unsupervised learning technique designed to decompose a neural network’s latent representations into sparse, seemingly interpretable features. While these models have ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results