HeyGen 联手 DeepMind 推出 Code2Video 基准，测模型代码生成视频
Models can write the code. Whether it renders into video worth watching is a separate question. Co...
模型会写代码不代表能渲出能看的视频，HeyGen 和 DeepMind 做了个新基准专测这件事。
HeyGen 宣布与 Google DeepMind、Kaggle 合作推出 Code2Video 基准，评估模型生成代码并渲染成可观看视频的能力。推文指出 SWE-bench 衡量的代码能力与代码到视频的呈现效果是两个不同维度。HeyGen 同时提到其 agentic 视频栈 HyperFrames 即构建在代码生成之上。
Models can write the code. Whether it renders into video worth watching is a separate question. Co...
Models can write the code. Whether it renders into video worth watching is a separate question. Code2Video bench measures that, built with google deepmind and @kaggle . HyperFrames @HyperFrames_ if you tried hyperframes, you would know the agentic video stack is being built on code-gen but SWE-bench code v.s. code-to-video that feels alive are two different things we built the Code2Video Bench, in collab w/ Google DeepMind & @Kaggle frontier labs can finally get good at agentic video tasks Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 3 🔄 1 ❤️ 2 👀 460 📊 3 ⚡
