view article Article autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training autotrust • 6 days ago • 59
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 8 days ago • 412
Realtime-Venus: A full-duplex interaction system with asynchronous delegation Paper • 2609.13814 • Published 24 days ago • 225
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published 27 days ago • 331