method
active
method:cross-modal-samplingCross-Modal Sampling
Technique used to demonstrate that the self-prior captures visual–proprioceptive associations by recovering visual appearance from proprioception alone
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Self-PriorsupportsThe key novel contribution: an internal model that learns the density of familiar multisensory experiences and drives mark-removal behavior through mismatch with the free energy principle
Claims (1)
claim
- Theoretical interpretation linking the self-prior to the established body schema concept
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.
- The alignment between representations learned from different data modalities such as vision and language
- The paper demonstrates the bidirectional geometry-behavior relationship across multiple tasks and modalities (language models and video world models)
- Key limitation of the formal PRH derivation: lossy or stochastic observation functions weaken the convergence guarantee
- Tunes PELT cost, penalty and kernel bandwidth by splitting S into folds.
- Validation of judge model robustness by regrading 1000 responses with 4 additional judge models
- Procedure for sampling 64 random nonnegative combinations of cone basis vectors to evaluate the full cone distribution
- Prediction 3 confirmed.
- Asymmetric transfer after fine-tuning: high-density bases (B10) are more robust.