Papers2

#instance segmentation

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

This paper upgrades a small but mighty vision-language model called PaddleOCR-VL-1.5 to read and understand real-world, messy documents better than any model before it.

#document parsing#vision-language model#layout analysis

LitePT: Lighter Yet Stronger Point Transformer

Intermediate

Yuanwen Yue, Damien Robert et al.Dec 15arXiv

LitePT is a new AI backbone for 3D point clouds that uses convolutions in early layers and attention in later layers to be both fast and accurate.

#LitePT#Point Transformer#3D point cloud