Cross-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

Active Inference with a Self-Prior in the Mirror-Mark Task
introduces

Frameworks (1)

framework

Self-Prior
supports
The 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

The self-prior is functionally analogous to the body schema: it captures cross-modal associations and directly guides action planning toward multisensory mismatch reduction
supports
Theoretical interpretation linking the self-prior to the established body schema concept

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Cross-Modal Alignmentconcept0.790
The alignment between representations learned from different data modalities such as vision and language
Cross-task and cross-modal validation of manifold steeringfinding0.752
The paper demonstrates the bidirectional geometry-behavior relationship across multiple tasks and modalities (language models and video world models)
The mathematical argument for cross-modal convergence strictly holds only for bijective projections of the underlying worldclaim0.751
Key limitation of the formal PRH derivation: lossy or stochastic observation functions weaken the convergence guarantee
Cross-Judge Analysismethod0.730
Validation of judge model robustness by regrading 1000 responses with 4 additional judge models
Monte Carlo Cone Samplingmethod0.729
Procedure for sampling 64 random nonnegative combinations of cone basis vectors to evaluate the full cone distribution
cross-base interferenceconcept0.725
Asymmetric transfer after fine-tuning: high-density bases (B10) are more robust.
cross-referenceconcept0.716
Explicit textual or graphical links between parts of a work, dynamic and virtual.
Multimodal-CoTframework0.714
A two-stage framework that separates rationale generation and answer inference by incorporating vision and language modalities.