PaddleOCR-VL-1.5 Collection Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing • 6 items • Updated 14 days ago • 10
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published 14 days ago • 182