Tencent relicenses its SOTA WeMM-Embedding models under Apache-2.0
NielsRogge · x · 2026-08-30
Tencent released its multimodal embedding family WeMM-Embedding this week with a technical report, now the top trending paper on Papers with Code, and updated the license to Apache-2.0. The models reportedly outperform Gemini Embedding 2, Qwen3-VL Embedding, and Voyage AI embedding models. See the companion link post for details.
More from Models
- Claude Code Shows Anomalous Speed: 150X Faster Than Normal — weswinder · 2026-08-30
- No Default Winner Anymore: Opus 5 Too Verbose, GLM and Kimi Win on Value — Yuchenj_UW · 2026-08-30
- GLM 5.3 Post-training Mechanics: Environment, RL, and Infra Explained — JohnAlexander · 2026-08-30
- GLM-5.3 Released for Agentic Coding at 30% Lower Cost — markjeffrey · 2026-08-30
- Critique of Ling-3.0-flash-Fin Benchmark: Configurations Matter More Than Wins — niacolhealth · 2026-08-30
- Hands-on with MiniMax M3 Multimodal Model — doodlestein · 2026-08-30