OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models Paper • 2607.28609 • Published 12 days ago • 68
ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published 5 days ago • 38
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models Paper • 2608.04964 • Published 6 days ago • 12
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 8 days ago • 155