Tencent Releases WeVisOne-VL Vision-Language Model for Unified Visual Tasks

Tencent's WeChat Vision team released WeVisOne-VL, an Apache 2.0 vision-language model in 2B and 4B sizes that handles detection, OCR, counting, segmentation and alpha matting in one model.

Read the full story at MarkTechPost ↗

Timeline · 1 report

2026-11-04 04:39 · MarkTechPost
Tencent WeVisOne-VL Unifies Detection, OCR, Segmentation and Matting

More stories

Tencent launches Hy4 open-weight AI model with vision and computer-use capabilities — SCMP China Tech
Oracle cancels $7 billion Tencent AI chip leasing deal under Trump administration pressure — Financial Times AI
Chinese AI firms' $70B Nvidia GPU orders face severe supply shortfall — Techmeme
LongCat 2.5 and Tencent Hy4 models now available on Vercel AI Gateway — Vercel Blog
Tencent releases open-source AI model trained with limited cybersecurity data — Reuters AI
Oracle scraps ~$7B deal to lease ~100K AI chips to Tencent after US pressure — Techmeme
Tencent Releases Foundation Model It Says Ranks Among China's Best — Bloomberg AI
Tencent reportedly preparing consumer AI search engine combining AI answers with web search — TechNode

Get the daily brief of stories like this at 6:30 every morning →