Tencent's WeChat Vision team open-sources WeVisOne-VL, a unified 2B/4B perception VLM
bdsqlsz · x · 2026-11-04
Tencent's WeChat Vision team released WeVisOne-VL, an open-source 2B/4B vision-language model unifying object-level perception (detection, counting, pointing, OCR) and pixel-level perception (segmentation, promptable alpha matting) via structured next-token prediction — no separate SAM needed, and it answers "None" for absent objects. 635 GitHub stars already.
More from Models
- Qwen, GPT and Gemini Flash all fail the same way on this service — matdryhurst · 2026-11-04
- Sub-1B open OCR models benchmarked: Surya 2.5 tops OmniParseBench at 85.9 — VikParuchuri · 2026-11-04
- Gemini 4 Carbon tested on Arena: near Opus on 3D and web design, still behind — altryne · 2026-11-04
- OCR on 2,165 pages of historic books: runaway loops down to 1, 1881 volume errors cut 38% — vanstriendaniel · 2026-11-04
- Median human turn-taking pause is -120ms, so voice AI's 500ms brag still misses how people talk — alexisgallagher · 2026-11-04
- Cloudflare Launches Clairic, a System One-Style Extraction Model Faster and Cheaper Than LLMs — michellechen · 2026-11-04