News

Neural Texture Compression demo shows it can do wonders for VRAM usage
Neural Texture Compression (NTC) is a new technique that improves texture quality while reducing VRAM usage. It relies on a specialized neural network trained to compress ...
IEEE28d
NISB-Fusion: Multi-Agent Mapping and Map Merging With Neural Implicit Spatial Block - IEEE Xplore
Recent advancements have demonstrated the potential of radiance representations for high-quality mapping and reconstruction. However, these methods face significant challenges in large-scale, ...
GitHub18d
cambridge-mlg/gridded-tnp: Gridded transformer neural processes - GitHub
Gridded Transformer Neural Processes A framework for implementing and reproducing the paper "Gridded Transformer Neural Processes for Spatio-Temporal Data" (ICML 2025) in Python. Setting up the conda ...
IEEE15d
Optimization of Power Transformer Defect Recognition Algorithm with Dga Based on Probabilistic Neural Network - IEEE Xplore
The trouble-free operation of power oil-filled transformer equipment is impossible without an effective diagnostic system. It is generally recognized that the chromatographic analysis of gases (DGA) ...
GitHub18d
GitHub - georgian-io/Multimodal-Toolkit: Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
A toolkit for incorporating multimodal data on top of text data for classification and regression tasks. It uses HuggingFace transformers as the base model for text features. The toolkit adds a ...