Ian Huang (@IanHuang3D)
2025-04-12 | โค๏ธ 28 | ๐ 1
If youโre wondering which multimodal LLMs you should be using to build 3D graphics agents ๐งโ๐ป , check out our CVPR2025 Highlight work, BlenderGym โ not only does BlenderGym benchmark the top open and closed models, it also reveals a trick about how you should be allocating your inference compute for graphical editing tasks. With this trick, open source models can beat close-source models on 3D graphics editing. Curious? ๐ง ๐ https://blendergym.github.io/
๐ ์๋ณธ ๋งํฌ
๐ Related
Auto-generated - needs manual review
์ธ์ฉ ํธ์
Yunqi (Richard) Gu (@richard_yunqigu)
Which multimodal LLM should you be using to edit graphics in Blender?
Today, weโre releasing our CVPR2025 Highlight๐ work, BlenderGym ๐๏ธโโ๏ธ, the first agentic 3D graphics editing benchmark that will tell you exactly how multimodal LLMs compare in their Blender-editing skills.
Whatโd we find? ๐งต๐
๐ฌ ์์
Tags
domain-vision-3d domain-rendering domain-ai-ml domain-vlm domain-visionos