VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation Paper • 2607.28590 • Published 7 days ago • 44
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 3 days ago • 145
Evaluation-Verification Reward for Consistent Multi-Reference Image Editing Paper • 2607.29025 • Published 6 days ago • 15