A single flow-matching diffusion transformer with explicit token roles and position types performs more than 30 audio-visual generation, editing, and reference-conditioned tasks without task-specific architectures.
Mmdisco: Multi-modal discriminator- guided cooperative diffusion for joint audio and video generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vorch-Omni: Multi-Task Orchestration of Sight and Sound
A single flow-matching diffusion transformer with explicit token roles and position types performs more than 30 audio-visual generation, editing, and reference-conditioned tasks without task-specific architectures.