Sparse snnTorch implementation of Fruit Fly (Drosophila Melanogaster) Brain
AI drug discovery on Apple Silicon. De novo generation + drug repurposing. 100% local, no cloud, fully auditable.
Structured State Matrix Architecture (SSMA) is a high-performance framework designed for efficient sequence modeling, combining structured state space models with adaptive attention mechanisms.
Run AI-driven drug discovery models locally on Apple Silicon. Protect your data without the need for cloud infrastructure or external GPUs.
Code and data for: Three Phases of Expert Routing — How Load Balance Evolves During MoE Training
Research — Mixture-of-Experts efficiency analysis. Benchmarking sparse activation vs dense models on cost-per-token and quality.
A controlled 180-run study of DeepSeek-inspired MLA, sparse MoE routing, V3-style load balancing, and multi-token prediction under constrained compute.
LiDAR point cloud completion for unstructured terrain in autonomous earthworks
Open MoE post-training factory for AI: expert sectors, forensics, ESFT/LoRA, data contracts, gated packages. Mixture-of-Experts fine-tuning toolkit.
Add a description, image, and links to the sparse-models topic page so that developers can more easily learn about it.
To associate your repository with the sparse-models topic, visit your repo's landing page and select "manage topics."