The paper introduces the Decan metric, a novel, information-theoretic approach for measuring creative diversity in AI outputs, which successfully detects diversity loss across different model fine-tun…

This paper investigates the benefits of generating multiple solutions in each generation for Evolutionary Diversity Optimisation (EDO) and proposes efficient methods to achieve it.

The paper introduces Banyan, a new continual reinforcement learning benchmark, demonstrating that while task diversity enables local transfer across distribution shifts, it does not guarantee sustaine…

The paper proposes a novel RL framework that naturally induces diverse agent behavior by reformulating the objective to treat the reward as a distribution over functions, making diversity a rational r…

This paper introduces a method for controlled diversity in text-to-image models, enabling semantic browsing and creative exploration through structured image galleries.

The paper introduces Diversity-inducing Initialization (DivIn), a novel method that improves image diversity by re-weighting the initial noise selection based on the guidance potential, thereby mitiga…

This paper investigates the correlation between gender diversity and the scientific impact of papers in Natural Language Processing (NLP) and Library and Information Science (LIS) domains.

The paper compares anchorless methods for diversifying LLM-generated idea pools against traditional anchor-dependent methods, finding that semantic direction stratification offers the best balance of…

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

This paper introduces Curvature-Weighted Gradient Diversity (CWGD), a geometry-aware measure for optimization noise that reduces the asymptotic optimization error floor by up to a factor of two compar…

This paper explores the effectiveness of diverse LLM-generated explanations versus generic explanations in computer science education, finding that diverse explanations led to higher open-ended respon…

This paper evaluates multiple LLMs (DeepSeek-R1, OpenBioLLM-Llama3, Qwen 3.5) for generating privacy-safe, high-quality synthetic mental health reports, demonstrating their effectiveness in expanding…

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge…

This paper examines how commercial voice AI systems reproduce and circulate gender performances through a listening experiment.

The paper introduces IndoBias, a dual-track, culturally-grounded benchmark to evaluate biases in LLMs across Indonesian and three local languages, revealing significant differences in bias patterns ac…

This paper proposes Evolutionary Intelligence (EI) for scientific discovery, which links candidate refinement with experience retention across evolutionary cycles.

This paper proposes an ensemble of two source separators, FTRNN and TF-Locoformer, trained with mixture invariant training (MixIT), and introduces mixture-constrained max pooling (MCM) to improve bird…

The paper audits six LLMs across four languages, finding that their gender stereotyping is significantly wider than human baselines and that cross-lingual translation fundamentally alters the nature o…