concept
active
concept:zhang-et-al-2023-storm-efficient-stochastic-transformer-based-world-models-neurips-2023Zhang et al. 2023: STORM: Efficient Stochastic Transformer based World Models (NeurIPS 2023)
World model framework extended and used in the present implementation
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Statistically rigorous analysis of Claude introspection; suggests models may have latent introspective capabilities that can be enhanced or disrupted.
- The core mechanism of LLMs: predicting the next token based on previous context.
- Source paper for Bayesian model reduction methodology used in structure learning
- Evidence that stages of inference emerge without training biases from retrofitting, recurrence scheduling, or multi-recurrence losses
- Organizing question for §6.2 on computational tools.
- Claim formalizing the Anima Labs idea that transformers are effectively recurrent due to K/V stream.
- Demonstrates that ecological networks can learn complex problem-solving without system-level selection
- Key validation that the process itself — not just site conditions — generates living structure.