LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 212
MinT: Managed Infrastructure for Training and Serving Millions of LLMs Paper • 2605.13779 • Published May 13 • 225
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator Paper • 2604.08121 • Published Apr 9 • 44
Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression Paper • 2506.09482 • Published Jun 11, 2025 • 45