fog composes LLM-generated motion functions (verbs/adverbs/gestures/emotions) so people recognize intended semantics in Heider-Simmel animations at 68% accuracy and iterate faster than pure prompting.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
fog: Expressing Motion and Emotion through Function Composition of AI-Generated Code
fog composes LLM-generated motion functions (verbs/adverbs/gestures/emotions) so people recognize intended semantics in Heider-Simmel animations at 68% accuracy and iterate faster than pure prompting.