HRM paper: 27M params, 1000 samples, near-perfect Sudoku and maze solving
burny_tech · x · 2026-11-10
The quoted post links the HRM paper (arXiv:2506.21734): a brain-inspired recurrent architecture with a slow abstract-planning module and a fast detailed-computation module that reasons in a single forward pass without CoT data. With only 27M parameters and 1000 training samples it nearly perfectly solves complex Sudoku and optimal maze pathfinding, and beats far larger models on the ARC benchmark.
More from Research
- Four Free Math Books for ML: Linear Algebra, Probability, Optimization, Information Theory — cneuralnetwork · 2026-11-10
- 4 free math books that actually matter for ML: linear algebra to information theory — cneuralnetwork · 2026-11-10
- Meta FAIR's e-means beats k-means in 1/10 epochs with 10-45x GPU speedups — burny_tech · 2026-11-10
- NeurIPS workshop paper: gradient-based data attribution can't reliably filter subliminal learning — ponguru · 2026-11-10
- Yang-Mills Working Group to Release OpenAI's Full Lean Code and Validation Tomorrow — burny_tech · 2026-11-10
- Interpretability researchers reminded: explanation matters, not just predictive power — burny_tech · 2026-11-10