Verified75% confidenceFactExact time
Gemini adopts a native multimodal architecture, jointly training the Transformer with mixed multimodal data from the pre-training stage, with tokens of different modalities processed together in the same sequence.
5
Sources
75%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
Related Claims
VerifiedThe Gemini series jointly models multiple modalities from the training stage, rather than appending a visual encoder as solutions like GPT-4V do.78% similarUnverifiedGemini mixes text, image, audio, and video data as input from the pre-training stage to achieve native multimodal training.77% similarUnverifiedGemini版本体系遵循双轴命名逻辑：主版本号代表架构或训练范式升级，规格后缀（Ultra、Pro、Flash、Nano）对应不同参数量级与部署场景75% similarUnverifiedGemini的图像生成能力基于原生多模态架构，模型在训练阶段同时学习了文本和图像的表征75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/480467API
curl https://kongchang.com/api/v1/knowledge/claims/480467MCP
get_claim(id=480467)