ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published 2 days ago • 24
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models Paper • 2608.04964 • Published 3 days ago • 10
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 5 days ago • 152