Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published 6 days ago • 185
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 15 days ago • 339
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published 7 days ago • 140
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published 22 days ago • 342
OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Paper • 2607.23193 • Published Jul 28 • 8