Baton introduces a multimodal VA-Planner that outputs semantically aligned planned tokens and Relative Semantic RoPE to coordinate denoising trajectories in joint video-audio diffusion generation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
Baton introduces a multimodal VA-Planner that outputs semantically aligned planned tokens and Relative Semantic RoPE to coordinate denoising trajectories in joint video-audio diffusion generation.