MotionGPT
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
Key pointsGenerates consecutive human motions from multimodal control signals via LLM instructions.
01
Motion quantization: Quantizes motion into discrete tokens that LLMs can produce in the same stream as text.
02
Multimodal control: Accepts text, audio, and other control signals as input, producing corresponding human motion outputs.
03
LLM-as-motion-generator: Treats motion generation as a token-prediction task, unifying motion with other LLM capabilities.
04
Animation and VR: Applicable to character animation, VR avatars, and content creation workflows where text-driven motion is valuable.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack