TextGrad performs automatic differentiation for compound AI systems by backpropagating natural-language feedback from LLMs to optimize variables ranging from code to molecular structures.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Dual-wavelength incoherent multiplexing enables native signed optical multiplication with constant overhead on lithium niobate, validated by 40 GHz bandwidth, 1.27% error, and neural network accuracies of 95.1% on Moons and 91.63% on MNIST.
citing papers explorer
-
TextGrad: Automatic "Differentiation" via Text
TextGrad performs automatic differentiation for compound AI systems by backpropagating natural-language feedback from LLMs to optimize variables ranging from code to molecular structures.
-
Scalable native signed optical computing enabled by dual-wavelength incoherent multiplexing
Dual-wavelength incoherent multiplexing enables native signed optical multiplication with constant overhead on lithium niobate, validated by 40 GHz bandwidth, 1.27% error, and neural network accuracies of 95.1% on Moons and 91.63% on MNIST.