A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization Paper • 2608.08156 • Published 6 days ago • 8
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining Paper • 2606.30634 • Published Jun 29 • 25
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models Paper • 2606.11324 • Published Jun 9 • 172
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433