TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 4 days ago • 127
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 12 days ago • 307
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 17 days ago • 205
Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions Paper • 2607.01283 • Published Jul 1 • 4
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published Jun 15 • 177
Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems Paper • 2606.18837 • Published Jun 17 • 58
Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published Jun 16 • 77
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published Jun 8 • 107