LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 212
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE Paper • 2606.32033 • Published Jun 30 • 7
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published Jun 15 • 178
Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness Paper • 2606.18874 • Published Jun 17 • 6
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue Paper • 2605.30993 • Published May 29 • 65
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards Paper • 2605.31584 • Published May 29 • 43
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433