Author

Dongchao Yang

h-index 13 View on Semantic Scholar

We have 2 of 32 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generation

SonicWeave is proposed, a flow-matching model for unified audio scene generation that supports speech, music, sound effects, singing, and their fine-grained mixtures with a single set of weights and suggests that temporally coherent, prior-evidence routing is an effective conditional-computation strategy for unified au...

Yun-Rui Cai, Xu Li, Yucheng Zhou et al. · 0 citations

Preprint Aug 2026

A Unifying Perspective on Audio Generative Modeling: Latent Representations and Modeling Strategies

This paper provides an evaluation and design framework for comparing representation-model pairs and shows that RVQ's residual order gives ordered capacity but not ordered semantics, and that AudioLM's semantic-versus-acoustic cascade is one explicit placement of this boundary rather than a universal template.

Dongchao Yang · 0 citations