PromptEvolver recovers high-fidelity natural language prompts for given images by evolving them via genetic algorithm guided by a vision-language model, outperforming prior methods on benchmarks.
In: Proceedings of the IEEE international conference on computer vision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A probabilistic unfolding network with stable likelihood projection and dual-domain Mamba achieves state-of-the-art reconstruction in quantized compressive sensing.
citing papers explorer
-
PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space
PromptEvolver recovers high-fidelity natural language prompts for given images by evolving them via genetic algorithm guided by a vision-language model, outperforming prior methods on benchmarks.
-
Deep Probabilistic Unfolding for Quantized Compressive Sensing
A probabilistic unfolding network with stable likelihood projection and dual-domain Mamba achieves state-of-the-art reconstruction in quantized compressive sensing.