<p>Senior adults are a growing population in America and face increased feelings of social isolation, a problem compounded by the COVID-19 pandemic. The positive physiological impacts of dance fitness classes for seniors are well documented, but less research exists on the impacts of creative dance on well-being and social connection. This study addresses this gap in knowledge by focusing on the expressive potential and social impact of senior adult engagement in creative dance. Over the course of a three-week dance and storytelling workshop, senior adult participants experienced an outlet for creative expression and imagination. The methods include oral history interviews, a group interview, facilitator field notes, oral storytelling, movement generation from language, creative writing exercises and somatic guided movement experiences. The study is situated within participatory action research (PAR), with regular dialogue and participant feedback guiding the workshop. In the context of community engaged dance, this research reveals the expressive potential that comes from bridging language and movement. I will show how utilizing both a “language-first” approach and a “movement-first” approach engaged the seniors’ imaginations in what Vygotsky terms “combinatorial creativity.” These approaches contributed to positive social connection outcomes and a sense of self-discovery among the senior adult participants and suggest the importance of imagination for creative expression in future community-based dance engagement.</p>

Generative systems that are based on emotions are a revolutionary approach in computational creativity because they allow the user to create visual artworks that are specific to the user and their emotional state. This paper will suggest a unified system wherein multimodal emotion recognition is integrated with powerful generative models to generate adaptive and expressive works of art. The system combines various modalities of inputs like facial expressions, voice signals and physiological data, and it detects and encodes emotions using deep learning networks such as convolutional neural networks (CNNs), long short-term memory (LSTM) networks and transformer based networks. An organized algorithmic sequence is proposed, including the parameterization, real time emotion recognition, feature encodings, and art creation that is adaptive. The experimental tests reveal dramatic enhancement of the accuracy of personalization, consistency in emotions, and interactivity when compared to conventional non-interactive systems of art. The results of visualization and case studies also prove the possibility of the system to dynamically change the artistic styles, color palette and compositions based on the preferences of particular users. This study presents the possibilities of emotion-sensitive generative models to reconfigure human-machine co-creation, provide scalable approaches to interactive digital art, therapeutic and immersive user-centered design spaces.

The application of artificial intelligence to creative processes has profoundly changed the modern digital art and illustration processes. Generative Adversarial Networks (GANs) are among many other AI approaches that have become potent in creating quality visual art and assisting the exploration of art. In this paper, the author explores the use of GANs as a creative collaborator in the digital painting and illustration workflow. The paper analyzes the technical principles behind GAN architectures, their use in the artistic image generation, and their role in human-AI creative processes. The most important applications of GAN systems, such as concept generation, style transfer, image-to-image translation, and automated colorization, are examined in order to comprehend how the technologies can support an artist at any phase of visual creation. The examples of major GAN models DCGAN, CycleGAN, StyleGAN, and StyleGAN2 are also compared to discuss the effectiveness of these models in the synthesis of artistic images. According to the results provided, it is seen that advanced architectures are better in image realism, consistency of structures and artistic usability than the previous models. Moreover, the study demonstrates the advantages of GAN-based tools as it promotes quick ideation, experimentation with styles, and design feedback, without taking control of the creative process of artists. The paper also talks of the technical structures of integrating GAN systems in the digital art setting and talks about issues of ethical issues surrounding authorship, originality, and bias in the dataset. All in all, the results indicate that the technologies based on GAN redefine the production of digital art by facilitating the interactive collaboration between human creativity and machine intelligence and creating new opportunities in the realm of innovations in computational creativity and digital illustration practice.

The current speed in generative artificial intelligence has brought major development to the creation of digital art, but the current models are in most cases incapable of producing true creativity because of their dependence on learned data distributions. This article introduces a new model, which includes quantum-inspired algorithms into the generative digital art models to foster creativity, diversity, and originality. Based on the ideas of superposition, probabilistic representation, and quantum-inspired optimization, the suggested solution refuses the latent space definition as a high-dimensional probabilistic landscape, which allows exploring various artistic options at the same time. The architecture has quantum-inspired encoding, annealing-like optimization and stochastic sampling sequences in traditional architectures of GANs and diffusion models. Test on experimental evaluation was done based on benchmark datasets such as WikiArt and large-scale art corpora. The suggested model was evaluated on the basis of not only quantitative measures like Fréchet Inception Distance (FID), Inception Score (IS), and a complex Creativity Index (CI), but also qualitative human evaluations. Findings prove that quantum-inspired model outcompares classical generative models in terms of lower FID scores, greater diversity, and much better novelty. User studies also conclude aesthetic appeal and originality of generated art works. The results suggest the prospect of quantum-inspired computation being a viable and realistic scalable method of further development of computational creativity. The research is valuable as it helps to develop a more expressive and innovative form of generative systems through the application of the ideas of quantum theory and artificial intelligence. In the future, it will be integrated with actual quantum hardware and multimodal creative uses.

Pre-production phase of visual art is a very significant stage because it entails intellectual ideation, story development and search of design. The need to possess smart looking systems that can be utilized to augment the traditional ideation work is growing as well as requirements of fast and diverse creative effort are escalating. The article dwells upon the application of Large Language Models (LLMs) to generate creative concepts in pre-production in visual art. With their abilities to manipulate and generate semantically rich textual data, LLCs are in a good position to be utilized to assist in supporting the early-stage artistic processes. The study proposes a formal methodology that would involve timely engineering, notion generation, and evaluation into a human-AI work system. System architecture is a developed system that assists in the conversion of user specified inputs to structured creative concepts like design of characters, descriptions of scenes and thematic scripts. The paper also explains how LLC can be incorporated with digital art tools in such a way that the ideation process through text may be incorporated into a visual representation without interruption. The obtained outcomes of the experiment show that the workflows that are assisted by LLM have a positive influence on the diversity, originality, and the quality of idea generation as compared to the traditional methods of idea generation. The generated concepts are evaluated using a detailed evaluation framework to assess the quality of the concepts generated by using various measures such as coherence, relevance, aesthetic potential and diversity. In addition, the user study, which will be carried out with artists and designers, will assist in receiving the concept of the practical applicability and usability of the offered approach. The findings demonstrate that LLMs can be regarded as efficient co-creative partners that help users overcome the issue of creative paralysis and expand the scope of their conceptual exploration without losing their artistic control. Despite these advantages, the originality, bias and creative evaluation problems are still present, which proves the need of more research. The discussion of the future directions, including multimodal integration, personalization of AI tools, and the development of the standardized ways of creativity measurement, conclude the paper. Overall, the work is applicable to the field of computational creativity as it demonstrates the possibility of using LLM to enhance the pre-production process related to the visual art and rebrand the human-AI collaboration in the creative industries.

The use of artificial intelligence in modern art is gaining more and more popularity; machines are able to produce visual data and be involved in creative processes. This paper examines how artificial intelligence is used as a creative partner in contemporary visual arts, specifically how generative models can support artists in the design of the concept and exploration of the artistic process. To encourage human-AI co-creation, a collaborative model that combines data preparation, generative AI models, interactive user interfaces and rendering modules is suggested. A dataset of 10,000 digital artworks that represent a variety of artistic styles was used to evaluate the experimentation. A generative model that runs on diffusion has been used to generate visual compositions in response to artist prompts. Findings show that AI-guided creative processes are highly time-saving and enhance the production time of artwork, as well as, stylistic and conceptual range. The comparative analysis shows that the rating of visual quality and artist satisfaction improves in case AI tools are introduced to the creative process. The results also demonstrate the possibility of artificial intelligence as a creative companion that can make humans more creative instead of stealing artistic status. The suggested framework helps in the evolving body of computational creativity because it will show how intelligent systems can supplement artistic processes and contribute to interactive creation of visual arts. The research offers information on how generative AI can be integrated into artistic space and outlines the future research prospects of immersive and interactive systems based on AI using creativity.

Artificial Intelligence (AI) has quickly changed the artistic production by allowing machines to produce images, music, literature, and multimedia works that mimic the work of humans with regard to creativity. The latest developments of machine learning, especially deep neural networks, Generative Adversarial Networks (GANs), and diffusion-based models, have increased what computational systems can do: creating complex artistic patterns based on massive data. Such developments have also brought up critical theoretical, legal, and philosophical issues of authorship, originality, and creative ownership on AI-generated artworks. This paper looks at the technical underlying principals of AI generated art and discusses the processes by which algorithms discover stylistic tropes, generate visual shapes and respond to human intervention in user prompts and parameter adjustment. The paper also discusses the changing argument over authorship in AI-generated art, which takes into account programmers, dataset curators, artists, and end users advantages in the creative pipeline. Moral and cultural considerations are also outlined, such as the issues concerning intellectual property, cultural biasness in training data, and the possible repercussion to the conventional artistic careers. With the combination of the views of computational creativity, the digital humanities and the cultural policy, the study points to the transformative paradigm of human-intelligent systems collaborativity of creativity.

This article advances a structural framework arguing that some mythological systems offer structural models that can illuminate aspects of contemporary creative processes in contexts marked by uncertainty, complexity, and ambiguity. Rather than proposing mythological belief or practice as a source of creative guidance, the article treats mythology as a cultural archive of cognitive structures that encode recurring patterns in human creativity. Drawing primarily on Hindu and Greek traditions, the analysis demonstrates that mythological configurations—such as the Ganesha–Yama dialectic and the system of the Nine Muses—anticipate and illuminate empirically validated dynamics in modern creativity research, including exploration–exploitation tensions, generative–selective cycles, domain specificity, and cross-domain synthesis. By integrating insights from structural anthropology, sociocultural creativity theory, computational creativity, and innovation studies, the article shows that mythological structures function as meta-procedural frameworks rather than prescriptive methods. These frameworks make visible liminal states, escalating constraints, and meaning-oriented judgment processes that remain undertheorized in contemporary models. The article concludes by arguing that structurally informed dialogue between mythological analysis and creativity research can enrich theoretical understanding without romanticizing or mystifying creative work.

In this paper, we describe the design and the methodological framework of a Language Creativity Test (LCT), whose aim is to assess linguistic creativity across humans and Large Language Models (LLMs). Based on recent research on human and computational creativity, this LCT evaluates the capacity to generate novel, meaningful, and contextually appropriate language. For human participants, the test measures imaginative linguistic performance, including metaphor generation, neologism creation, and flexible word use, which are considered key indicators of divergent thinking and linguistic fluency. For LLMs, the same tasks serve to determine their creative language generation and test the extent to which they go beyond learned patterns to produce original expressions. Thus, the LCT described here enables direct comparison of creative language use between biological and artificial systems, offering insights into how creativity manifests across different types of intelligence.

This study critically updates Marshall McLuhan’s media theory to analyze the mental, sociological, and artistic effects of generative artificial intelligence, understood as a radical cognitive extension that reconfigures perception, identity, and cultural production. A qualitative approach based on comparative conceptual analysis is employed. Foundational texts by McLuhan are examined in dialogue with recent scholarship in neuroscience, algorithmic sociology, and computational creativity studies. McLuhan’s tetrad is systematically applied as an interpretative framework. Findings indicate that AI externalizes cognitive processes such as synthesis and writing, enhancing efficiency while activating the Law of Reversal. Risks of digital amnesia, cognitive sedentarism, and the erosion of deep reading are identified. Sociologically, the “global village” evolves into algorithmic fragmentation and a surveillance capitalism model. In the artistic domain, authorship becomes decentralized and creativity is redefined in terms of statistical recombination. AI emerges as a structural media environment whose efficiency may reverse into intellectual dependency and conformism. The study underscores the need for anticipatory governance and renewed critical media literacy to safeguard human agency.

Paradoxism is an avant-garde literary/artistic movement centered on contradictions, absurdities, antinomies, deviations of sense, upside-down interpretations etc. as creative principles. The movement spans literature, art, philosophy, even science, and it aims to challenge conventional thinking and express the complexity and contradictions of reality. Paradoxism is examined here not merely as an avant-garde literary movement, but as a trans-historical literary meta-system grounded in contradiction as a productive aesthetic principle, initiated by Smarandache in 1980. Drawing upon paraconsistent and neutrosophic logic, this paper argues that Paradoxism operates beyond Modernism and Postmodernism by formalizing paradox as both method and meaning. Through comparative analysis with major literary movements, logical axiomatization, and conceptual diagrammatic models, Paradoxism is shown to function as a universal operator acting upon literature itself. Rather than resolving inconsistency, Paradoxism preserves and intensifies it, allowing meaning and non-meaning to coexist. The paper concludes by extending Paradoxism into contemporary theory and artificial intelligence, positioning it as a generative framework for future literary and computational creativity. Below is a concise comparison with other movements, highlighting key contrasts.

In this narrative review, we examine the persistent demand for innovation in haute cuisine and the considerable psychological costs of sustaining the creativity it requires. We outline the multiple factors that contribute to culinary creativity and emphasise the continuing importance of the human touch, particularly given that forms of so-called computational creativity, such as digital gastronomy or algorithmic food-pairing, have so far delivered limited practical value. We also consider the constraints inherent in the often-invoked synaesthetic approach to creative practice in the arts. Looking to the future, we highlight the promise of multisensory design informed by emerging insights into crossmodal correspondences as one pathway for supporting certain kinds of culinary innovation. Sensory, psychoactive, and organisational or strategic strategies for enhancing creativity are also reviewed. Finally, we draw attention to the psychological costs and consequences for those who must maintain high levels of creative output in the kitchen over extended periods.

Hedonic requirements, which specify a user’s intended emotional response, are critical to success in many types of software, games, and interactive experiences. By surveying over 300 IT project managers, we reveal a strong link between their perception of these requirements and project success, highlighting the need for better methods to manage emotional goals.

The recent surge of Large Language Models (LLMs) has led to claims that they are approaching a level of creativity akin to human capabilities. This idea has sparked a blend of excitement and apprehension. However, a critical piece that has been missing in this discourse is a systematic evaluation of LLMs' semantic diversity, particularly in comparison to human divergent thinking. To bridge this gap, we leverage recent advances in computational creativity to analyze semantic divergence in both state-of-the-art LLMs and a substantial dataset of 100,000 humans. These divergence-based measures index associative thinking-the ability to access and combine remote concepts in semantic space-an established facet of creative cognition. We benchmark performance on the Divergent Association Task (DAT) and across multiple creative-writing tasks (haiku, story synopses, and flash fiction), using identical, objective scoring. We found evidence that LLMs can surpass average human performance on the DAT, and approach human creative writing abilities, yet they remain below the mean creativity scores observed among the more creative segment of human participants. Notably, even the top performing LLMs are still largely surpassed by the aggregated top half of human participants, underscoring a ceiling that current LLMs still fail to surpass. We also systematically varied linguistic strategy prompts and temperature, observing reliable gains in semantic divergence for several models. Our human-machine benchmarking framework addresses the polemic surrounding the imminent replacement of human creative labor by AI, disentangling the quality of the respective creative linguistic outputs using established objective measures. While prompting deeper exploration of the distinctive elements of human inventive thought compared to those of AI systems, we lay out a series of techniques to improve their outputs with respect to semantic diversity, such as prompt design and hyper-parameter tuning.

As artificial intelligence (AI) becomes an increasingly integral part of daily life, equipping younger generations with the tools and knowledge to understand and create with AI is essential. This paper presents the design, development, and evaluation of a children-oriented AI design platform that enables users to create, test, and deploy machine learning (ML)-driven applications with minimal coding knowledge. The platform focuses on intuitive visual programming interfaces, age-appropriate ML model training workflows, and real-time deployment capabilities. Through iterative user testing with children aged 8–14, the system was refined to prioritize usability, engagement, and educational value. The platform integrates pre-built AI models for tasks such as image recognition, text classification, and voice commands, while also allowing customization and experimentation. Our results demonstrate the platform’s effectiveness in fostering computational thinking, design creativity, and basic AI literacy. We conclude with insights into designing child-friendly AI tools and propose future directions for expanding accessibility and curriculum integration.

This study presents a comprehensive network meta-analysis (NMA) of 16 empirical studies comparing listener evaluations of human-performed traditional music to three types of AI-generated renditions (generic AI, fine-tuned AI, and hybrid AI-human). Following PRISMA-NMA guidelines, we synthesized Hedges' g effect sizes for aesthetic ratings (e.g., beauty, authenticity, and likeability) across these conditions. Network geometry reveals a fully connected loop (Human–Generic–Fine–Hybrid). Results show that human performances were rated significantly more favorably than purely generic AI renditions (g≈+0.60, 95% CI [0.35, 0.85]), with moderate advantages over hybrid (g≈+0.20) and smaller differences versus fine-tuned AI (g≈+0.10). Fine-tuned AI slightly outperformed generic AI (g≈–0.40), and hybrid AI (combining AI and human elements) also modestly exceeded generic AI (g≈–0.30). These effect sizes (small to medium, according to Cohen's conventions) suggest that anthropomorphic elements (animacy, human-like "fit") drive preference, aligning with research showing that human-like AI voices boost likability. We discuss the implications for science and STEAM education: algorithmic music can serve as a vehicle for AI literacy and computational creativity in curricula, but educators must address concerns about perceived authenticity and fairness. Drawing on insights into anthropomorphism and Cheng's recommendations for AI in music education, we argue that science educators should incorporate AI-generated music thoughtfully—using it to engage students in computational thinking, ethics, and digital literacy, while also considering the equity of access. The paper concludes with future directions on ethical design, inclusivity, and the evolving role of AI in musical learning and science pedagogy.

This study presents an interactive AI-driven framework for real-time piano music generation from human body motion, establishing a coherent link between physical gesture and computational creativity. The proposed system integrates computer vision–based motion capture with sequence-oriented deep learning to translate continuous movement dynamics into structured musical output. Human pose is extracted using MediaPipe, while OpenCV is employed for temporal motion tracking to derive three-dimensional skeletal landmarks and velocity-based features that modulate musical expression. These motion-derived signals condition a Long Short-Term Memory (LSTM) network trained on a large corpus of classical piano MIDI compositions, enabling the model to preserve stylistic coherence and long-range musical dependencies while dynamically adapting tempo and rhythmic intensity in response to real-time performer movement. The data processing pipeline includes MIDI event encoding, sequence segmentation, feature normalization, and multi-layer LSTM training optimized using cross-entropy loss and the RMSprop optimizer. Model performance is evaluated quantitatively through loss convergence and note diversity metrics, and qualitatively through assessments of musical coherence and system responsiveness. Experimental results demonstrate that the proposed LSTM-based generator maintains structural stability while producing diverse and expressive musical sequences that closely reflect variations in motion velocity. By establishing a closed-loop, real-time mapping between gesture and sound, the framework enables intuitive, embodied musical interaction without requiring traditional instrumental expertise, advancing embodied AI and multimodal human–computer interaction while opening new opportunities for digital performance, creative education, and accessible music generation through movement.

The advancement of digital illustration has led to a revolution stage whereby it entails the application of generative artificial intelligence which integrates the human creativity and the computational creativity. In this paper, the shift towards generative ecosystems via models such as GANs, VAEs, and diffusion networks will be considered in relation to the transformation of the conventional workflows of vectors and raster. It suggests an ambivalent framework based on which the illustration is regarded as a multidimensional contact between human mental will and machine learning inference. In order to estimate the similarity of artwork produced with the help of AI and human-produced artworks in terms of the aesthetic and semantic quality, the paper proposes a Creative Performance Index (CPI) as a critical combination of Fréchet Inception Distance (FID) and CLIP Score and the human-based measurements of originality and emotional resonance. Through a number of case studies of applications like DALLE, Stable Diffusion and Midjourney, it has been demonstrated in the paper that coaching of human feedback based on an iteration approach has a profound impact on artistic containment and richness of ideas. The findings validate that generative AI does not replace the agency of the illustrator but expands it to make the creative process adaptive and symbiotic system of leading to ideas, contemplating on them, and perfecting them.

With the fast adoption of artificial intelligence in the art and cultural industry, the production, curation, distribution, and management of creative works have been radically transformed. Intelligent systems that allow artists, curators, institutions, platforms, and intelligent systems to work together in continuous interaction are now known as AI-driven art ecosystems. The paper explores management innovation as it manifests in AI-based art systems, the changes in managerial practices, forms of governance and decision making, in reaction to advanced computational creativity and data-driven work. The paper conceptualizes AI-based art systems as multi-layered systems that include creative production, curatorial intelligence and digital distribution systems such as online galleries and non-fungible token-based markets. It emphasizes the ways in which management innovation is developed in the form of a workflow redesign that combines automation and human-AI partnership to allow efficiency without sacrificing artistic intent and cultural sensitivity. Additionally, the paper focuses on the governance innovations that respond to the issues of transparency, accountability, ethical compliance, and authorship attribution in creative settings with algorithms mediating them. The resource orchestration is considered a key managerial competency with a focus on the strategic alignment of data resources, innovative talent, and computing resources. The study further examines the AI-enhanced decision-making in the context of art institutions and how the predictive analytics and the intelligent recommendation systems can be used in audience engagement prediction, curatorial planning, and portfolio management. Based on the selected case studies of AI-integrated museums, hybrid creative studios, and global AI-art hubs, the paper finds the best practices and benchmarking perspectives.

The fast development of the generative artificial intelligence has considerably altered the modern artistic operations, posing the essential concerns about the matter of originality, authorship, and artistic worth of the AI-generated products. Although AI systems can create visually attractive and stylistically varied results, it is a more pressing problem how to judge whether these were original creations or just recombinations of acquired information. This analysis suggests a holistic analysis of originality in AI modern art by joining the computational evaluation with human analysis. The study constructs originality as a multidimensional phenomenon that covers novelty, non-traditionality, intention to create something new, and relevance to its contexts in terms of cultural and historical reference space. The proposed framework is based on the theories of computational creativity and human-AI co-creativity, but it also considers the shared authorship models where originality is created through the interaction between artists, datasets, algorithms, and curatorial choices. The originality assessment model based on AI is presented and is a combination of visual, semantic, stylistic, and contextual feature extraction with embedding-based similarity and divergence analysis. The quantitative measure of originality in terms of novelty scores, stylistic distance measures and entropy based diversity measures are used to represent the structural and statistical aspects of originality. These calculation tests are then complemented by qualitative tests such as the art experts, curators and audience perception studies in order to cover the subjective and interpretive aspects which most automated programs fail to cover. A comparative study of AI-based evaluation and traditional originality assessment methods shows the advantages and the constraints of the former.