MiniWorld: Democratizing the Training of Video World Models from Scratch Paper • 2608.01127 • Published 11 days ago • 19
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging Paper • 2608.03316 • Published 9 days ago • 26
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 10 days ago • 155
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems Paper • 2607.29241 • Published 13 days ago • 11
Evaluation-Verification Reward for Consistent Multi-Reference Image Editing Paper • 2607.29025 • Published 13 days ago • 16