Unverified50% confidenceFactExact time
Microsoft's ClimaX explores a pre-training and fine-tuning paradigm based on the Vision Transformer.
1
Sources
50%
Confidence
Long-term
Relevance
8/8/2026
First Seen
Sources
谷歌WeatherNext登Nature：AI气象模型预测台风路径领先24小时
Related Claims
Unverified文生视频模型通常基于扩散变换器（Diffusion Transformer）架构，将运动先验与外观风格解耦处理67% similarUnverifiedCommunity developer Cseti trained an IC-LoRA model named LTX2.3-22B_IC-LoRA-CrossView-Prompt based on LTX 2.3, which can use prompt guidance to have the AI regenerate footage of the same scene from a different camera angle.65% similarVerifiedVision Transformer（ViT）由Google Brain团队于2020年提出，将Transformer架构引入计算机视觉领域64% similarUnverified动作识别领域经历了从手工特征（光流、HOG）到深度学习（双流网络、I3D、SlowFast）再到基于Video Transformer的范式转变64% similarUnverifiedFlux是由Black Forest Labs推出的新一代图像生成模型，基于Transformer架构64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/712682API
curl https://kongchang.com/api/v1/knowledge/claims/712682MCP
get_claim(id=712682)