concept
active
concept:mixed-generative-modelsMixed Generative Models
Generative models combining discrete and continuous states to link decisions and movements.
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Generative Modelrelated_toAgent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.
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.
- Globally-acting model that recursively monitors and updates how all inference layers interact; substrate of epistemic depth
- Proposed future method: fit active inference generative models to AI behavior to verify wise world model internalization
- Features related to gender, racial, ethnic biases, slurs, and hate speech.
- Central challenge for active inference stated in Discussion.
- A set of instructions for making something (contrasted with a descriptive blueprint), as in embryonic development.
- The computational approach used to simulate morphogenesis with cells as agents on a 2D grid; allows quantitative testing of stress-sharing hypothesis.
- Large pretrained models for genomic sequences; subject of this work's pooling improvements.
- Second model system studied; used to show why flat autoregressive LLMs struggle with long-range coherence.