SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Paper • 2607.20145 • Published 1 day ago • 35
The Underappreciated Power of Vision Models for Graph Structural Understanding Paper • 2510.24788 • Published Oct 27, 2025 • 36
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16, 2025 • 129
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE Paper • 2510.13344 • Published Oct 15, 2025 • 65