concept
active
concept:sequence-poolingSequence pooling
General technique for aggregating variable-length token embedding sequences into fixed-length representations; mean pooling and covariance pooling are instances.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Mean PoolingextendsStandard baseline aggregation method that covariance pooling improves upon; discards joint activation structure.
Artifacts (1)
artifact
- Goodfire research post introducing covariance pooling as a replacement for mean pooling in genomic foundation models; shows +52.9% R² lift on genomic track prediction.
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.
- A shared repository (the Internet) where morphogenetic sequences are stored, exchanged, mutated, and improved by the public.
- The interdependence of morphogenetic sequences, where each triggers others to repair the whole environment, analogous to arithmetic operations.
- A morphogenetic sequence for direct architect management of tilework, incorporating the fifteen transformations into design and laying steps.
- Novel aggregation technique replacing mean pooling; preserves joint activation structure (feature co-occurrence) in token embeddings.
- Aggregation of token-level activations.
- A list-level prompting baseline that asks for k responses in a single call without probability verbalization
- Server feature letting users type sequences and view head attention; not open-sourced.
- An ordering of patterns and transformations that, when followed, can conjure up a whole geometric world