MiniWorld: Democratizing the Training of Video World Models from Scratch Paper • 2608.01127 • Published 5 days ago • 13
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging Paper • 2608.03316 • Published 3 days ago • 24
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 4 days ago • 150
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems Paper • 2607.29241 • Published 7 days ago • 10
Evaluation-Verification Reward for Consistent Multi-Reference Image Editing Paper • 2607.29025 • Published 7 days ago • 15