arXiv Machine Learning
Jul 27
Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability
arXiv:2607.
Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction
Diffusion TV is an interactive AI art installation that transforms a CRT TV into a tangible interface for diffusion models. By physically adjusting the TV’s antenna, users control the clarity of AI-generated images and sounds, symbolically mirroring the denoising process that underlies diffusion-based generation. The installation offers three channels—Past, Present, and Future—featuring AI-generated animals, allowing participants to explore intermediate states of the generative process through continuous audiovisual feedback.
Related stories
arXiv AI
Sep 24
Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound
Passing is an interactive audiovisual installation that transforms a single continuous monorail-window recording into an endless journey by reconstructing it as a spatiotemporal volume and resampling its spatial and temporal structure along nonlinear trajectories. A camera-based viewer‑presence detection system influences transitions among rendered video sequences, and the resulting video stream is fed into SpecMaskFoley, a real‑time video‑to‑audio synthesis model that generates a synchronized soundscape. The work distributes creative agency among the artist, the AI model, and the audience, exploring how authorship and listening can be negotiated among human intention, machine inference, and audience interpretation.
arXiv AI
Jul 14
Model Collapse: On Recursion, Noise, and Uncharted Machine Visions
arXiv:2607. 09705v1 Announce Type: cross Abstract: Since 2023, computer scientists have warned against model collapse -- the contamination of training sets with AI-generated outputs that progressively degrade model performance.
arXiv AI
Jun 9
WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI
arXiv:2605. 16972v2 Announce Type: replace-cross Abstract: Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement.
Hugging Face Trending Papers
Aug 25
Representation Learning in Diffusion and Flow-based Model: An Application Aspect
Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, multi-level visual representations through large-...
arXiv AI
Jun 2
Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
arXiv:2601. 00664v2 Announce Type: replace-cross Abstract: Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation.
arXiv Machine Learning
Sep 15
Real-time Learning and Evolution in Robotic Art Installations
arXiv:2609.13352v1 Announce Type: cross Abstract: We present three robotic art installations which explore the aesthetics of adaptive behavior. Through embodied machine leaning and digital evolution,...
arXiv AI
Aug 5
AI-Based Sound Effect Generation: A Narrative Review of Generative Models Across Input Modalities
arXiv:2608. 03742v1 Announce Type: cross Abstract: Sound effects play a crucial role in conveying actions, events, and environmental cues across digital applications, often requiring a high degree of variation and contextual adaptability.
arXiv AI
Jul 7
CoGen3D: An Agentic Human-AI Co-Design Pipeline for 3D Asset Generation for Virtual Reality
arXiv:2607. 03731v1 Announce Type: cross Abstract: Creating 3D assets for virtual reality requires modeling expertise, which restricts the authorship of immersive experiences.
arXiv AI
Jul 16
Grounded world models in biological organisms and future embodied AI
arXiv:2607. 13560v1 Announce Type: cross Abstract: Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data.
arXiv Computer Vision
Aug 26
Representation Learning in Diffusion and Flow-based Model: An Application Aspect
The article surveys how diffusion and flow-based generative models learn rich visual representations and how these representations can be used to improve generation and other perception tasks. It introduces a three-tier framework that categorizes work into improving generative quality via representation learning, extracting representations for perception, and developing unified applications. The survey covers downstream tasks such as image classification, dense prediction, instance-level perception, and annotation-scarce scenarios, offering a taxonomy and highlighting future research directions.
arXiv AI
Jul 8
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
arXiv:2605. 13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood.