cross-modal-transfer

Researchers at MIT Lincoln Laboratory propose 'principle-driven foundation models' that encode signal-theoretic physical principles (Fourier decomposition, energy conservation, symmetry) instead of learning statistical correlations from large paired datasets. Trained exclusively on RF data, their 1.99M parameter frozen encoder achieves 77.7% average accuracy across 15 diverse tasks spanning audio, images, text, and video without any fine-tuning on target domains.