SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation Paper • 2610.22264 • Published Oct 15 • 31
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published Sep 30 • 134
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published Aug 26 • 37
Running Featured 564 Agent Memory Leaderboard 🧠 564 Unified memory evaluation · Results expected August 12.