Tencent WeVisOne-VL Unifies Detection, OCR, Segmentation and Matting

Este es el extracto disponible del feed. Puede estar abreviado o en el idioma original.

Tencent’s WeChat Vision team has released WeVisOne-VL, an open vision language model in 2B and 4B sizes. The WeVisOne-VL vision language model handles detection, referring, counting, pointing, OCR, segmentation and alpha matting in one model. Pixel outputs come from a 9.6M-parameter decoder, so no separate SAM is needed. It also answers “None” when a queried object is absent. For developers, that can replace a detector, an OCR engine and a segmenter with one model. TL;DR Size: 2B (2.44B params) and 4B (4.83B params) on Hugging Face, and a 9.6M-parameter pixel decoder. Trained with up to 8,192 tokens of context; deployment context length is not disclosed. Runs on: A single GPU through Transformers or vLLM in BF16. The package also lists NPU and CPU devices. VRAM needs are not disclosed. A community GGUF ran object-level tasks on a 6 GB RTX 2060. Performance: Beats the same-scale VLM baselines in Tencent’s tables on most of 30+ benchmarks (self-reported). Best: 71.3 F1 Mean on Dense200 dense detection, versus 58.7 for LocateAnything-3B. Worst: 52.6% rejection rate on PR-Bench, so many absent-target queries still get a box. What is WeVisOne-VL? WeVisOne-VL (“WeChat Vision All-in-One”) is a perception-focused model from Tencent built on Qwen3-VL. It targets fine-grained localization rather than open-ended chat. Users choose the output granularity: points, boxes, binary masks or continuous alpha mattes. How does WeVisOne-VL work? Every task is cast as structured next-token prediction. The model adds coordinate tokens to for normalized boxes and points. An absent target produces None instead of a guessed box. For pixel tasks, the model emits an token after each predicted box. Its hidden state becomes a query for the pixel decoder, according to the model card. The decoder has 3 parts: Visual Feature Adapter: reuses multi-level Qwen3-VL ViT features instead of a second image encoder. Box-Guided Query Decoder: 6 deformable cross-attention blocks seeded by th