Qianfan-OCR: A Unified End-to-End Model for Document Intelligence Paper • 2603.13398 • Published 8 days ago • 123
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation Paper • 2603.16669 • Published 1 day ago • 64
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas Paper • 2603.16448 • Published 1 day ago • 44
Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression Paper • 2512.05081 • Published Dec 4, 2025 • 32
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising Paper • 2603.08703 • Published 9 days ago • 31