TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation
For researchers and practitioners in music-dance co-generation, TMD-Bench provides a standardized evaluation framework that addresses the overlooked problem of rhythmic alignment, highlighting gaps in current models.
TMD-Bench introduces a multi-level benchmark for text-driven music-dance co-generation, evaluating unimodal quality, instruction adherence, and cross-modal rhythmic alignment. It reveals that commercial models like Veo 3 and Sora 2 produce high-quality outputs but lack consistent rhythmic coupling, while the proposed RhyJAM baseline achieves competitive beat-level synchronization.
Unified audio-visual generation is rapidly gaining industrial and creative relevance, enabling applications in virtual production and interactive media. However, when moving from general audio-video synthesis to music-dance co-generation, the task becomes substantially harder: musical rhythm, phrasing, and accents must drive choreographic motion at fine temporal resolution, and such rhythmic coupling is not captured by unimodal metrics or generic audiovisual consistency scores used in current evaluation practice. We introduce TMD-Bench, a benchmark for text-driven music-dance co-generation that assesses systems across unimodal generation quality, instruction adherence, and cross-modal rhythmic alignment. The benchmark integrates computable physical metrics with perceptual multimodal judgments, and is supported by a curated rhythm-aligned music-dance dataset and a fine-grained Music Captioner for structured music semantics. TMD-Bench further reveals that (i) modern commercial audio-visual models, such as Veo 3 and Sora 2, produce high-quality music and video, while rhythmic coupling remains less consistently optimized and leaves room for improvement, and (ii) our unified baseline RhyJAM trained on rhythm-aligned data achieves competitive beat-level synchronization while maintaining competitive unimodal fidelity. This presents prospects for building next-generation music-dance models that explicitly optimize rhythmic and kinetic coherence.