Public KG record
WeVisOne-VL
Recorded overview
A perception-focused VLM in 2B and 4B sizes built on Qwen3-VL, featuring a 9.6M-
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Capabilities: detection
- Capabilities: OCR
- Capabilities: segmentation
- License: Apache 2.0
- Supported types: image input
- Supported types: text input
- Supported types: points, boxes, binary masks, or continuous alpha mattes output
Evidence coverage
The KG currently records 9 known information dimensions and has 10 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Tencent — develops
- LISA-13B — competes with
- LocateAnything-3B — competes with
- PP-OCRv5 — competes with
- SAM2-Matting — competes with