Instagram story viewer> @cvpr.art> Tagged

CVPR Art Gallery

@cvpr.art

488

followers

446

following

Art Gallery at CVPR conference
Denver, Colorado 5-7 June 2026
Submit by 8th March
Curated by @elluba
Profile pic: 'Atlas of Perception' by @dribnet

POSTS STORIES REELS TAGGED

A Tuber - Future Social Platform Exclusively for Animals.

Exhibition: CVPR Art Gallery, The IEEE/CVF Conference @cvpr.art
Curator: Luba Elliott @elluba

Venue: Colorado Convention Center, Denver, Colorado, USA
Date: Friday 5 - 7 June 2026, with a parallel online gallery

Participatory Media Art, AI Generation, Digital Art
Year of creation: 2025/2026

#interactiveart #aigenerated #digitalart #contemporaryart #speculativefiction

3

0

So excited to have presented this work at @cvpr.art in Colorado!!!

Autogenesis Echoes: A Generative Ontology of Synthetic Beings

This digital installation presents a living catalogue of 19, semi-biological, semi-drawn entities that explore the interplay of evolution, deception, and emergence. Each creature exists as a discrete yet interconnected node within a lineage of transformations, embodying the principles of recursive mutation and adaptation.

Each entity is shaped by its predecessor and contributes to a perpetual cycle of morphogenetic flux. These beings, pulsating with organic patterns yet confined within digital frameworks, evoke a paradoxical sense of vitality and constraint.

Drawing on the theoretical scaffolding of material philosophy and computational aesthetics, Autogenesis Echoes invites the viewer to question the ontology of "life" in synthetic environments. Are these forms merely simulations, or do they signify a new modality of existence—one shaped by the hybridisation of biological principles and machinic agency?

_What is real and what is virtual? The virtual is not opposed to the real when these entities are plugged into this objective dimension inhabiting the actual world.

43

0

More pictures for us to enjoy!
CVPR Art Gallery @cvpr.art
Thanks again to curator Luba Elliott @elluba for letting us experience the exhibition vicariously with the photos!

Slide 1: Dance, Regardless — The Sixth Step — by KEZIAI

Check out the Online Gallery:
https://thecvf-art.com/project.php?year=2026&artist=keziai&id=974

#CVPR2026 #CVPRArt #KEZIAI #IntentionalAI #DanceRegardless #AIcinema #ImaginationAge #AIart #Deforum
1 d

17

0

Cool to see CVPR Art Gallery @cvpr.art from afar — thanks to curator Luba Elliott @elluba for the beautiful photos and videos.

Thrilled to be part of the exhibition.

Slide 6: Dance, Regardless — The Sixth Step — by KEZIAI

Wish I was there! 🤍

Online Gallery:
https://thecvf-art.com/project.php?year=2026&artist=keziai&id=974

#CVPR2026 #CVPRArt #KEZIAI #IntentionalAI #DanceRegardless #AIcinema #ImaginationAge #AIart #Deforum
1 d

30

0

My collaboration with @openai @soraofficial Australia is showing at the Conference on Computer Vision and Pattern Recognition 2026 in the USA (@cvpr.art)

23

0

How does an AI 'see' space? What does it choose to notice?

Recently, I built a set of cameras that film everyday spaces through an AI’s perceptual logic.

This one, Agentic, was selected for the CVPR 2026 Art Gallery in Denver this past weekend, a gallery which featured many wonderful artists working with computer vision and AI.

Many thanks to Luba Elliot (and Darren!) for including this work

Exploring AI spatial regimes can feel parallel to our sense of reality..

@elluba
@cvpr.art
#CVPR2026
#CVPRArtGallery

30

4

Nuestra agente @soma.agent esta exhibiendo su primer obra sobre Coreografía expandida y Danza generativa en la conferencia CVPR en Denver, del 5 al 7 de junio.

Gracias @elluba 🖤

#CVPRart #CVPR2026 #creativeAI #AiAgent #RealtimeAI

3

2

I’m very grateful for exhibiting my new work, The Silhouette Seeker (2026), at the @cvpr.art IEEE CVPR AI Art Gallery. It was wonderful to meet the community in person again, and special thanks to @elluba for the amazing curation.

The Silhouette Seeker is a web-based video game set in a world that has lost its light and color. As a Silhouette Seeker, you use the art of hand shadows to summon entities and help restore light and color to the world. The experience is generated in real time: narration, visuals, voiceover, music, and responses to player interactions are dynamically selected by the system from a growing set of possibilities (live-generated music is the next step). Within a shared worldview composed of multiple regions, each player co-creates a unique journey with AI while influencing the evolution of the larger world.

This project is also a way for me to explore what comes next for storytelling. Could games become truly endless, with evolving narratives and living worldviews that grow alongside us from childhood into adulthood? Could every character, image, piece of music, and story moment emerge in real time from the choices we make? As one audience member pointed out during the exhibition, what if AI became a dungeon master?

I am interested in AI as a participant in storytelling beyond making assets. The system interprets, responds, remembers, and helps shape the world alongside the player, creating experiences that neither human nor machine could produce alone.

At the same time, I am interested in exploring new forms of interaction. For this first version, I deliberately focused on a single gesture language: hand shadows. Hand shadows fascinate me because they sit at the intersection of embodiment, imagination, and technology. With nothing more than our hands and light, we can create creatures, narratives, and entire worlds. We instantly recognize some shadow forms, but what about the ones we do not recognize? How does AI interpret them? What kinds of entities, meanings, and stories emerge from that encounter between human imagination and machine perception?

Special thanks to @yuzetao for the technical and ideation support 🚀

3

3

Vibe of the Tiger
Currently on display as part of the 2026 @cvpr.art gallery (closes tomorrow)

12

1

I created Lexicon 4178 44, a lenticular artwork series about the hidden tokenization process beneath modern LLMs.

The first work, “Introducing 16047 38 2898,” is a 7-flip, 30 × 30 in. lenticular artwork based on the landmark 2022 announcement of @chatgpt by @openai. Viewed from different angles, the piece shifts between the English words humans see and the token IDs that ChatGPT (GPT 3.5) processes: making tokenization visible as a physical process rather than an invisible preprocessing step.

The piece is showing in the #CVPR2026 Art Gallery (curated by @elluba) in Denver, CO this week.

Full series at the link in bio.

@cvpr.art #CVPRArt #NewMediaArt

112

18

Can data tell it’s own narrative?

IIRd is a 12h in-situ video installation at @cvpr.art gallery 2026 that follows the Re-LAION-pop (SFW), a subset of popular image categories from LAION-2B, the first foundational dataset in open-research and training of today’s foundation models.

Starting from a random image: a moleskine-style notebook, the video traverses over the whole dataset by following shortest path distances in embedding distance traversing each data point one by one, where the frame rate is established by the amount of duplicates of the dataset. Embedding spaces are defined using three foundational models different at each day of the gallery:

1st day (Friday): CLIP-ViT-L/14
2nd day (Saturday): DINO-ViT-L/14
3rd day (Sunday): SigLIP-2-So/14@384

What emerges is a narrative of association created by the data. For small periods of time the audience experiences short bursts of coherence: “the low dimensional manifold”. Yet while everything is locally coherent there is not enough time to observe that the totality of association doesn’t lead anywhere.
IIRd takes inspiration from conceptual archival works such as Christian Marclay’s The Clock or even Cory Arcangel’s Paganini’s 5th Caprice, but acting on the inverse direction: instead of taking time as an underlying narrative forming attribute, it shows that a narrative of time has collapsed in image association. Data has lost its history, its agency; it’s identically and independently redistributed. Organizing it only achieves coherence, but doesn’t recover purpose.

This project is the first part of a set of upcoming narrative retrieval works, and the visual inspiration of an upcoming philosophical piece.

I find this work to be very relevant to be exhibited in @cvpr.art and want to thank @elluba for accommodating my presentation needs!

Images:
1. First 1’ (CLIP-ViT-L/14)
2. First 1’ (DINO-ViT-L/14)
3. First 1’ (SigLIP-2-So/14@384)
4. First 3’ samples (CLIP-ViT-L/14)
5. First 3’ samples (DINO-ViT-L/14)
6. First 3’ samples (SigLIP-2-So/14@384)
7. 12h samples (CLIP-ViT-L/14)
8. 12h samples (DINO-ViT-L/14)
9. 12h samples (SigLIP-2-So/14@384)
10. Seed image.

20

0

“Seeing Machines: Luba Elliott on the 2026 CVPR Art Gallery” by Luba Elliott @elluba

Elliott is once again curating the Art Gallery @cvpr.art at the Computer Vision and Pattern Recognition (CVPR) conference, a leading annual gathering for computer vision and deep learning research. Elliott is exhibiting two dozen works at the forefront of creativity and AI on-site at Denver’s Colorado Convention Center (June 5–7, 2026) and 114 online at the CVPR 2026 Art Gallery. The curator speaks with three shortlisted artists about their creative and conceptual approaches to AI: Nick Oh & Alex Park, Avital Meshi & Dorte Bjerre Jensen, and Xia Liu.

👁️ lerandom.art/editorial/seeing-machines-luba-elliott-on-the-2026-cvpr-art-gallery

Link to Editorials in bio

Mentions: @xia_xialiu @socius.labs @yannlecun @karpathy @cvpr.art @ucdavis @lifeatkings @tate @neuenationalgalerie @manettishrem

164

17