QD-LLM applies neuroevolution to prompt embeddings within a quality-diversity framework, producing 46% higher coverage and 41% higher QD-score than QDAIF on HumanEval, MBPP, and creative writing benchmarks.
Fontaine and Stefanos Nikolaidis
2 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
2
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Superquadrics parametrization combined with MAP-Elites produces the highest QD-score for diverse and functional robot designs across two test environments compared to CPPN and standard EA baselines.
citing papers explorer
-
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
QD-LLM applies neuroevolution to prompt embeddings within a quality-diversity framework, producing 46% higher coverage and 41% higher QD-score than QDAIF on HumanEval, MBPP, and creative writing benchmarks.
-
Generation of Diverse and Functional Robot Designs using Superquadrics Parametrisation and Quality-Diversity
Superquadrics parametrization combined with MAP-Elites produces the highest QD-score for diverse and functional robot designs across two test environments compared to CPPN and standard EA baselines.