Tencent releases WeVisOne-VL, unifying object- and pixel-level visual perception
tencent · hf · 2026-10-23
Tencent released WeVisOne-VL, a vision-language model that unifies object-level and pixel-level perception via structured token prediction.
- Supports detection, grounding, counting, OCR, segmentation, and matting in one model
- Uses a lightweight pixel decoder and multi-stage training
- Open 2B checkpoint built on Qwen3-VL, covering reasoning segmentation, referring matting, dense detection and more
Related event: Tencent Open-Sources WeVisOne-VL for Unified Visual Perception(3 posts)→
More from Models
- Local LLM benchmark drama: unrepeatable scores spark call for AIPerf standard — TheZachMueller · 2026-10-23
- Dev plans to point an abliterated local model at his smart TV to strip spyware — TheZachMueller · 2026-10-23
- Claude $200 plan delivers 45.3x API value, author denies Anthropic quota cut — RexDouglass · 2026-10-23
- User slams OpenAI's GPT-6.1 Sol: 20 hours lost, ignores human feedback — RexDouglass · 2026-10-23
- Dexmal's open-source VLA model DM0.5 lands in LeRobot, tops RoboColiseum — AdinaYakup · 2026-10-23
- Gemini tip: enable agentic video understanding for ~90% lower token usage — patloeber · 2026-10-23