STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published Sep 29 • 75
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published Sep 27 • 53
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 130
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published Sep 27 • 81
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation Paper • 2609.34759 • Published Sep 28 • 24
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 235