concept
active
concept:latent-reasoninglatent reasoning
Reasoning approach using learnable hidden embeddings.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Statement of existing alternatives to direct generation.
Concepts (2)
concept
- latent methodsassociated_withMethods that use latent reasoning; lack task generalization and are difficult to train with autoregressive parallelization.
- learnable hidden embeddingsassociated_withThe component used in latent reasoning to perform internal computation.
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.
- Statistical regularities stored in pretrained models.
- Entities that become visible as centers in a configuration (e.g., rectangles of white space around a dot) that were not present before.
- Hidden or underdeveloped structures existing 'between the lines' of a configuration that can be enhanced and developed through harmony-seeking computation.
- Output of alignment map ϕ applied to DNN hidden states; basis for distributed causal abstraction
- Baseline method using a single orthogonal matrix trained to map source latents to target latents via CL auxiliary loss without behavioral objective.
- Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.
- The paper's central construct: a vector in LLM activation space encoding the transition between reflection levels.
- Configurational entities existing implicitly in a structure; guide perception and generation of next morphogenetic step; exemplified in St Mark's square cycles.