A frozen vision-language model more than doubles its accuracy on precise visual-computation questions by writing Python code and refining plain-text skills from its own failed executions.
PAL: Program-aided language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Self-Evolving Code-with-Image Reasoning
A frozen vision-language model more than doubles its accuracy on precise visual-computation questions by writing Python code and refining plain-text skills from its own failed executions.