# Cross-Modal Monotonic Alignment

The work introduces Align Then Reason (ATR), in which a monotonic CTC alignment scorer between candidate-text phonetic units and frame-level lip representations supplies per-unit soft tokens and a calibrated global alignment score to an LLM reasoner that outputs a Yes/No judgment with a short explanation, raising Qwen3.5-9B mean AUC from 0.610 to 0.920 on a seven-language benchmark and improving on three unseen MuAViC languages and two real dubbing downstream tasks.

The work introduces Align Then Reason (ATR), in which a monotonic CTC alignment scorer between candidate-text phonetic units and frame-level lip representations supplies per-unit soft tokens and a calibrated global alignment score to an LLM reasoner that outputs a Yes/No judgment with a short explanation, raising Qwen3.5-9B mean AUC from 0.610 to 0.920 on a seven-language benchmark and improving on three unseen MuAViC languages and two real dubbing downstream tasks.