Reflections on Mechanical Creativity       Walter Benjamin’s 1935 essay The Work of Art in the Age of Mechanical Reproduction argued that technologies like photography and film transformed how art is created and perceived, eroding its unique “aura” tied to a specific time and place. Today’s advent of artificial intelligence represents a comparable upheaval: […]

Liminal (2024)  This animated music video for Imitate is a meditation on liminal space and the feeling of passing between worlds. I started with video of the artist performing in front of a green screen, which I keyed out and placed into dreamlike environments built from camcorder footage I shot in Joshua Tree. The desert […]

Compositionality and Parts Kenan Tang, 2024, Digital illustration using SPICE   I created this artwork in response to a blog post by AI critic Prof. Gary Marcus. The blog post identified AI models’ weaknesses in understanding the compositionality and parts of common objects. AI models were believed to be unable to reliably create common objects with […]

Methodical Random is an iterative exploration of visual recursion and material transmutation, where my archival body of mixed-media photography is continually deconstructed and regenerated through a meticulously structured yet inherently unpredictable generative workflow. At first, prints of my work are dissected, paired, and intercollaged before being metabolized by generative AI. Without inputting any textual prompts, […]

💖heartsleeves (2024) 💖heartsleeves is a multifaceted generative video project. Part one is code-based, abstract video art that then becomes the basis for community portraits once minted. In this layered generative process, the artists take advantage of the distributive nature of art on the blockchain to elevate the community to co-creators who can generate their own […]

The Digital Heartbeats (2025) An exploration into the often-overlooked transient states of silicon circuits, where the space between digital clock pulses reveals unexpected complexity and beauty. This 3-minute visual study examines TinyTapeout circuits generating VGA signals for video effects and games, rendered through a custom GDSII to gate-level simulation workflow. The visualization pairs WebGL 3D […]

Random Access Memory (RAM) In this 2 part video artwork, the artist looks at abstraction through the contemporary lens of machine aesthetics. Grounded in his practice of exploring machine intelligence and emergent aesthetics for over a decade now, the artist works with intergenerational and inter-geographical representations of abstraction art. Can we teach machines the aesthetics […]

Sigmara is a generative image process that probes the threshold between legibility and abstraction. Using feature recognition algorithms to reveal hidden structures in form and texture. These unseen patterns reshape the image, altering its original form without erasing its presence. Rather than simply blending two images, Sigmara synthesizes them: one offers structural contours, the other […]

ReVerie Pinyao Liu, Keon Ju Lee The ReVerie interactive AI Performance explores the scientific concept of dream reliving, and translates whispered dream recollections into real-time visualizations of dream objects using a 3D generative diffusion model, allowing participants to explore a shared “dreamscape”.   During the performance, visitors engage in a ritualistic act of whispering their […]

Encrypted Visions The project was created using My Art My Choice (MAMC), an AI art protection tool developed by Rhodes et al. and published in CVPR ’24 (“My Art My Choice: Adversarial Protection Against Unruly AI”). MAMC generates adversarially “protected” versions of images by applying gradient-based perturbations that mislead diffusion models like Stable Diffusion, causing […]

Of Style Bees and Beehives 2025 Our animation artifact is built around the concept of clustering visual artworks to elicit new ‘styles’ in an artwork collection. It illustrates the play of ‘neural representation‘ in creating unique style definitions in the deep learning models. We do this by building an allegory with ‘bees in a beehive‘. Style […]

(un)stable equilibrium 2:1 (un)stable equilibrium is an ongoing series of works that are borne out of an artistic practice developed around the training of generative neural networks without any training data. In this second series of works (2025), the process of training is borne out in the video pieces — with each work in the […]

RXALITI is a new AI art collection by Atay Ilgun, and a thematic continuation of the artist’s landmark 2019 work Realiti, widely regarded as the first AI-generated artwork on Ethereum with its own smart contract. This twin/body of work explores the widening chasm between online reality and simulation [🕳”fractal-n3t rips⛓ the ve!l of $imul@tion”], the […]

Soundscape Thresholds: AI Hallucinations Reimagining the Sacred Experience of Ming Rituals Ziwei Chi     This video work explores how AI-generated hallucinations can recreate the spiritual dimension of the “unseen soundscape space” in Ming Dynasty heaven-worship rituals. Based on studies of Jiajingera ceremonial music, the ritual constructs a liminal space for divinehuman dialogue through specific […]

Music for AI Audience (2024 ->) is a collaborative piece between custom deep learning software and a musician. It’s a 10-15 minute live performance based on a feedback loop between the improvising musician and the AI audience. The audience consists of multimodal LLM agents. Captioning what they see or hear, the audience members observe the […]

Patch Explorer, 2025 Patch Explorer is an interactive interface that lets users explore and manipulate the hidden layers of diffusion models. Inspired by interpretability techniques, Patch Explorer allows users to interact with the hidden states of a model by directly manipulating its activations. The diffusion process takes place in the latent space, where images are […]

Gradient Canvas (2025)An AR Community Art Project Gradient Canvas is an augmented reality (AR) community art project that blurs the boundaries between the physical and digital worlds through collective creativity. In the physical space, the artwork presents an empty canvas with the inscription: “This is not a painting” — a playful homage to René Magritte’s […]

Latent handstyles In this work I explore the use of the Contrastive Language-Image Pre-training (CLIP) model to drive the generation of traces that resemble graffiti tags. The CLIP model encodes images and their corresponding text-captions in a shared latent space. Here I am “exploring” this space in conjunction with an adaptation of the Sigma-Lognormal model […]

NEURAL LANDSCAPES 2025 Augmented Reality + Machine Learning   muPoint, a creative project designed in collaboration with Artificial Intelligence, explores the intersection of human cognition and AI through the fusion of augmented reality, machine learning, and real-time device sensors. In this work, we trained an AI model on Filipe Rocha da Silva’s textile drawings, creating […]

Through the Eyes of Involution This image was generated during the development of my Trans-Involution deep learning network for building rooftop extraction. The model integrates Involution blocks, which guide the network to focus on the most informative regions of the image—such as structural edges and meaningful textures—enhancing its ability to distinguish buildings from their surroundings. […]

Embodied / Divergent 2024 Embodied / Divergent is an interactive digitial artwork that connects human touch with the latent architecture of an AI system. As visitors use the touch interface, their interaction subverts and shapes the AI’s internal processes – disrupting its usual behaviour and revealing unexpected visial outcomes. By making the invisible mechanics of […]

Re-annotate Zihou Ng, 2025 One of the common visual conventions in computer vision is the use of geometric annotations overlaid on images—such as bounding boxes for object detection or keypoints for human pose estimation. These annotations reflect how machine learning models operate: extracting, compressing, and reducing information from unstructured raw data. In ML-related artworks, this […]

Percussive Complexity 1, 2025 Improvised visual music composition, with stereo sound, based on the model of 4 regions of increasingly complex systems: static, looping, complex, and chaotic. Dale E. Parson, January 2025, made with Processing & Java MIDI libraries. Static: Of the 4 complex regions, Static is the most basic. Iterative: Of the 4 complex regions, […]

Leibniz’ Cinematography of Folding If one wants to unfold Deleuze – Leibniz to fold back ones own folding in order to arrive at the level of processuality, one follows a line that finds complications in the concepts in order to counter-fold them. To move along the level of folding in and out and to understand […]

Fetal Movement Artist Name: Bomin Kwon, On Lee, Tongtong Li, Yoonah Song Year of Production: 2024 AI animation film Duration : 7:50 Artist Bio:  We (Bomin Kwon, On Lee, Tongtong Li, Yoonah Song) are as a team, currently working on using AI tools to create an image of a world that is abstract, and doesn’t […]

In this interplay between human and machine, between imperfection and intention, we glimpse an aesthetic that is neither purely artificial nor entirely natural. It is a digital Wabi-Sabi—a quiet acceptance of the incomplete, the fleeting, and the beautifully flawed.

WARPED is a 2024 three-part compilation by artist Guli Silberstein, in which artificial intelligence is used to warp and bring to life static images into creepy, lyric, and hallucinatory scenes. This practice engages with a history of body distortion in painting, from the deformed forms of Francis Bacon to the vertiginous spatial intelligence of Surrealism, […]

Activated Fragments -parallelized- (2024) Scott Allen ABOUT 　Like a “upside-down picture”, the same object can be interpreted as something completely different when viewed from different directions. At this moment, the original spatial connections are fragmented and systematized into something else, which is interpreted by the human mind. I wondered if the abstraction of the picture, […]

Ephemeral Memory Traces (2025-)  The long-term project ‘Ephemeral Memory Traces’ aims to enable artificial intelligence to reminisce about their memories. A memory may fade away in the flow of life, only to return unexpectedly. This project seeks to embody this paradoxical nature of memory.   ⏚ single-channel video, colour, 16:9,  3’03”, 2025 Ephemeral Memory Traces […]

Illusion3D We create 3D multiview illusion art using 2D text-to-image generation model. What is Illusion3D? More examples and technical details at https://3d-multiview-illusion.github.io/. Personal website: https://yuefeng21.github.io/  

Embodied Ink: A Multisensory Reinterpretation of Chinese Calligraphy Through Digital Performance Project Year: 2024 Project Website: https://mystudio.design/embodied-ink Key words: Chinese calligraphy, motion capture, generative AI, biometric feedback, multimedia performance  Artists: Anna Borou Yu, Jiajian Min Dancers: Ying Shi, Greta Campo   Embodied Ink Dance Performance at 2024 NEW INC DEMO Video Manifesting as a two-dimensional artform, Chinese Calligraphy […]

The Mundane and the Sublime (2025) is a curious exploration of the blurring boundaries between the common and the extraordinary. This digital artwork examines how the everyday fragments of life can be transformed into creations of striking beauty, evoking the grandeur of art’s most celebrated masterpieces. Simultaneously, it questions this transformation by reversing the process—reshaping […]

AttnMod AttnMod is a novel technique for generating unique, unpromptable art styles by modifying the attention mechanisms within existing diffusion models. By adjusting attention multipliers in specific UNet attention blocks during the denoising process, AttnMod enables the creation of diverse visual outputs without altering the original model weights or prompts. This approach allows for the […]