structured-decoding

SheetSage2 is a unified music transcription framework combining synthetic MIDI supervision, task-specific structured decoding, and autoregressive distillation, outperforming prior systems on 12 of 15 benchmark-metric pairs with publicly available model weights and code.

JevSpawn introduces a compositional policy that maps natural language task specifications to finite probabilistic exploration, using parallel action spawning and feedback-driven branch selection to speed up and improve LLM agent inference without additional training, evaluated on eight benchmark tasks against seven baselines.