concept
active
concept:feedback-loops-from-internal-model-representationsFeedback loops from internal model representations
Mechanism of using internal activations or representations to create corrective feedback during generation.
Neighborhood — ranked by edge-count
Methods (1)
method
- Self-Correcting SearchimplementsTechnique using internal model representations as feedback loops to steer diffusion-based materials generation toward target properties.
Concepts (1)
concept
- Internal model representationsassociated_withThe latent activations or embeddings inside a neural network.
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.
- Key dimension analyzing how wide the gulfs of execution and evaluation are in a system and how they relate; uses concepts from The Design of Everyday Things.
- Core question motivating interchange intervention and interpretability research supported by pyvene
- Query topic combining consciousness theory with cyclical self-monitoring processes.
- High-dimensional vectors produced at each transformer layer for each input token; the primary substrate analyzed in this study.
- A model mapping outputs to expected inputs, used in motor control and perception for embodiment.
- Mechanism speculation for the intentional control experiment.
- The causal hypothesis motivating the use of causality (intervention) as the lens connecting representation and behavior geometry.
- A representation that maintains stable activation across many tokens rather than being locally triggered by specific content