An environement builder for hierarchical reasoning research
PyTorch implementation of the Hierarchical Reasoning Model with Adaptive Computation Time (HRMACT) for solving Sudoku puzzles, with pretrained checkpoints available on Hugging Face . Supports training, inference, and evaluation with curriculum learning across difficulty levels.
Intent classification framework based on Dempster-Shafer (DS) theory, designed for uncertainty-aware, hierarchical decision-making
Hierarchical Reasoning Model Official Release
A theoretical framework for constructing adaptive, hierarchical layers of knowledge processing in AI. This model enables dynamic restructuring of knowledge systems, supporting scalable learning and meta-reasoning. AIにおける知識処理を階層的かつ適応的に構築する理論モデル。知識体系の動的再構成を可能にし、スケーラブルな学習とメタ認知的推論を支援する。
Research scaffold for hierarchical re-reading, latent memory consolidation, and teacher-guided distillation in PyTorch.
Add a description, image, and links to the hierarchical-reasoning topic page so that developers can more easily learn about it.
To associate your repository with the hierarchical-reasoning topic, visit your repo's landing page and select "manage topics."