The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 146
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published Sep 27 • 53
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations Paper • 2609.32522 • Published Sep 26 • 20
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation Paper • 2609.34759 • Published Sep 28 • 24
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published Sep 27 • 81
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published Sep 9 • 164