HybridMythos: Hierarchical Recurrent-Depth Transformer HybridMythos is an open-source, theoretical architecture that merges the infinite-depth looping of OpenMythos with the brain-inspired, dual-timescale cognitive processing of the Hierarchical Reasoning Model (HRM).
🔧 Recurrent-Depth Transformer Research Lab — LTI-stable looped inference, switchable MLA/GQA attention, MoE routing & adaptive halting (ACT). Independent research, not affiliated with Anthropic.
HelixLM - a recurrent heterogeneous graph neural LLM combining biological neural column random wiring, hybrid attention, and Mamba-2 for hyperpersonalized and on-device AI.
Research recurrent-depth transformer architectures with this modular PyTorch framework for efficient sequence modeling.
Add a description, image, and links to the openmythos topic page so that developers can more easily learn about it.
To associate your repository with the openmythos topic, visit your repo's landing page and select "manage topics."