method
active
method:hierarchical-reasoning-model-hrmHierarchical Reasoning Model (HRM)
Cited small (7M param) recurrent model that outperforms >10B-parameter LLMs on ARC-AGI, motivating the paper's focus on reasoning dynamics.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Fractal basins trap latent reasoningcitesmentions
Datasets (1)
dataset
- Visual-puzzle benchmark used with TRM to probe fractal basins, and cited as evidence for reasoning models' efficiency.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Models of sensory generation that allow dynamic context-sensitive prior expectations.
- Enable brain to construct dynamic, context-sensitive prior expectations; foundational to perceptual inference scheme.
- Globally-acting model that recursively monitors and updates how all inference layers interact; substrate of epistemic depth
- Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
- An ordering of texts via spatial cues like indentation, size, and placement, implying importance.
- Demonstrated CNN representations predict neurons in visual cortex; background motivation for neural-network-brain correspondence.
- Architecture iterating a single latent to a fixed point via residual threshold; used on Sudoku and mazes.