RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published 6 days ago • 20
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Paper • 2609.04199 • Published 7 days ago • 378
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models Paper • 2608.10538 • Published 30 days ago • 15
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference Paper • 2608.10288 • Published about 1 month ago • 7
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory Paper • 2608.04530 • Published Aug 5 • 14
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing Paper • 2608.02711 • Published Aug 3 • 93
QQWorld: Quantile-Quantile Matching for World Model Regularization Paper • 2607.28415 • Published Jul 30 • 31