Tootfinder

Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative Models
Ole Hall, Anil Yaman
https://arxiv.org/abs/2403.19620 https://

Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative Models
Generative Adversarial Networks (GANs) have shown great success in generating high quality images and are thus used as one of the main approaches to generate art images. However, usually the image generation process involves sampling from the latent space of the learned art representations, allowing little control over the output. In this work, we first employ GANs that are trained to produce creative images using an architecture known as Creative Adversarial Networks (CANs), then, we employ an…

Here’s a nice overview of all the anti-#AI tools available to visual artists today.
https://www.theverge.com/24063327/ai-art-protect-images-copyright-generators…

How to keep your art out of AI generators
Here’s how you can opt out of training some of the more popular generative AI models, or use tools like Glaze and Nightshade to protect art that’s used without permission.

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
Saptarshi Chakraborty, Peter L. Bartlett
https://arXiv.org/abs/2401.15801

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
Despite the remarkable empirical successes of Generative Adversarial Networks (GANs), the theoretical guarantees for their statistical accuracy remain rather pessimistic. In particular, the data distributions on which GANs are applied, such as natural images, are often hypothesized to have an intrinsic low-dimensional structure in a typically high-dimensional feature space, but this is often not reflected in the derived rates in the state-of-the-art analyses. In this paper, we attempt to bridge…

Semi-Supervised Learning for Deep Causal Generative Models
Yasin Ibrahim, Hermione Warr, Konstantinos Kamnitsas
https://arxiv.org/abs/2403.18717 https://…

Semi-Supervised Learning for Deep Causal Generative Models
Developing models that can answer questions of the form "How would $x$ change if $y$ had been $z$?" is fundamental for advancing medical image analysis. Training causal generative models that address such counterfactual questions, though, currently requires that all relevant variables have been observed and that corresponding labels are available in training data. However, clinical data may not have complete records for all patients and state of the art causal generative models are unable to ta…

"But it can be useful, like for summaries!"
Meanwhile, 99.9% of generative AI usage is for replacing authors and editors with garbage writing, outright scams, flooding search engines with shit, ripping off artists, cheating on writing assignments, firing translators, creating pornographic images of people who didn't consent, generating CSAM, stealing other people's code and advancing the fine art of low effort enshittification.

This https://arxiv.org/abs/2402.12531 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Improving Deep Generative Models on Many-To-One Image-to-Image Translation
Deep generative models have been applied to multiple applications in image- to-image translation. Generative Adversarial Networks and Diffusion Models have presented impressive results, setting new state-of-the-art results on these tasks. Most methods have symmetric setups across the different domains in a dataset. These methods assume that all domains have either multiple modalities or only one modality. However, there are many datasets that have a many-to-one relationship between two domains.…

This toot captures a tiny bit of the fun and potential for satire behind generative language art, back before the extractive VC pirates descended
https://mathstodon.xyz/@sc_griffith/110749575739905416

How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation
Andr\'e Ferreira, Naida Solak, Jianning Li, Philipp Dammann, Jens Kleesiek, Victor Alves, Jan Egger
https://arxiv.org/abs/2402.17317

How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation
Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which is difficult to obtain, especially in the medical field. Therefore, our solutions address this problem by using unconventional mechanisms for data augmentation. Generative adversarial networks and registration are used to massively increase the amount of available samples for training three different deep learning models for brain tumour segmentation, the first…

An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi, Taejoong Chung, Peng Gao, Murtuza Jadliwala, Bimal Viswanath
https://arxiv.org/abs/2404.16212

An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly available deepfake datasets. In this work, we study 8 state-of-the-art detectors and argue that they are far from being ready for deployment due to two recent developments. First, the emergence of lightweight methods to customize large generative models, can enable …

This toot captures a tiny bit of the fun and potential for satire behind generative language art, back before the extractive VC pirates descended
https://mathstodon.xyz/@sc_griffith/110749575739905416

Via Vincent Proce on Twitter on AI:
“This is making the rounds!” (On #AIArt)

Sci-fi author Adrian Tchaikovsky at #aiuk: When you outsource any part of your creative work, be it to a generative “AI” or another human, it means you are not improving your skills, art is a craft that needs to be improved.

What’s your favorite art* bot account on Mastodon and why should I follow it?
*does not include generative AI stuff

This https://arxiv.org/abs/2401.16268 has been replaced.
link: https://scholar.google.com/scholar?q=a

A.I. In All The Wrong Places
This text describes experiences gained across a two-year test period during which two generations of Generative Artificial Intelligence (A.I.) systems were incorporated into an interdisciplinary, university level course on A.I. for art and design practices. The text uses the results from the courses to reflect on new opportunities for generative systems in art and design, while considering traps and limits.

Starting in 1 hour (4:30 EDT), Christiane Paul draws on decades of experience as the Whitney Museum's Curator of Digital Art to share insights on how AI will impact artists and how, conversely, artists continue to probe the boundaries of AI.
Register at https://maine.zoom.us/webinar/register

Been slacking posting more art here, so time for a teensy selection of an old generative/evolutionary system from 2014 (then used for my HOLO 2 magazine guest design). Originally written in Clojure, meanwhile ported to TypeScript & Zig, I've kept working on & experimenting with it ever since... 1000s of screenshots and 100s of versions to sift through. Loosely based on research done by Barricelli[1] since the early 1950s, conceptually and aesthetically it sits nicely between my C…

Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence
Timothy R. McIntosh, Teo Susnjak, Tong Liu, Paul Watters, Malka N. Halgamuge
https://arxiv.org/abs/2402.09880

Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence
The rapid rise in popularity of Large Language Models (LLMs) with emerging capabilities has spurred public curiosity to evaluate and compare different LLMs, leading many researchers to propose their LLM benchmarks. Noticing preliminary inadequacies in those benchmarks, we embarked on a study to critically assess 23 state-of-the-art LLM benchmarks, using our novel unified evaluation framework through the lenses of people, process, and technology, under the pillars of functionality and security. …

Can we please stop calling it “AI art”?
1. Art is created by humans.
2. Hiring an artist and telling them what approximately you’d like isn’t art. (What the artist produces is art.)
3. Machines aren’t human.
Therefore, generative algorithms categorically cannot produce art as a product, and a prompt isn’t art in itself.

tune your ears towards new horizons with last night's frow show on @…, 3 hours of #freeform #radio for uplifting gormandizers, featuring much excellent new music (including

This https://arxiv.org/abs/2309.06358 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
Robustness in Natural Language Processing continues to be a pertinent issue, where state of the art models under-perform under naturally shifted distributions. In the context of Question Answering, work on domain adaptation methods continues to be a growing body of research. However, very little attention has been given to the notion of domain generalization under natural distribution shifts, where the target domain is unknown. With drastic improvements in the quality and access to generative m…

Foundation Models and Information Retrieval in Digital Pathology
H. R. Tizhoosh
https://arxiv.org/abs/2403.12090 https://arxiv.org/pd…

Foundation Models and Information Retrieval in Digital Pathology
The paper reviews the state-of-the-art of foundation models, LLMs, generative AI, information retrieval and CBIR in digital pathology

There’s a neat new core library in CircuitPython: `bitmapfilter`. Originally designed for the PyCamera project, it’s got many useful operations for generative art stuff like I do in Processing/p5js. Here’s a start: random circles bluring away. note, it does require a fast processor like the ESP32-S3 as on this great Lilygo board. Code:

starting to play with bitmapfilter in CircuitPython for Processing- / p5js-like effects
starting to play with bitmapfilter in CircuitPython for Processing- / p5js-like effects - bitmapfilter_play1_code.py

There’s a neat new core library in CircuitPython: `bitmapfilter`. Originally designed for the PyCamera project, it’s got many useful operations for generative art stuff like I do in Processing/p5js. Here’s a start: random circles bluring away. note, it does require a fast processor like the ESP32-S3 as on this great Lilygo board. Code:

Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment
Zhaoyang Wang, Bo Hu, Mingyang Zhang, Jie Li, Leida Li, Maoguo Gong, Xinbo Gao
https://arxiv.org/abs/2402.14401

Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment
Existing free-energy guided No-Reference Image Quality Assessment (NR-IQA) methods still suffer from finding a balance between learning feature information at the pixel level of the image and capturing high-level feature information and the efficient utilization of the obtained high-level feature information remains a challenge. As a novel class of state-of-the-art (SOTA) generative model, the diffusion model exhibits the capability to model intricate relationships, enabling a comprehensive und…

This https://arxiv.org/abs/2403.08701 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Review of Generative AI Methods in Cybersecurity
Large language models (LLMs) and generative artificial intelligence (GenAI) constitute paradigm shifts in cybersecurity that present hitherto unseen challenges as well as opportunities. In examining the state-of-the-art application of GenAI in cybersecurity, this work highlights how models like Google's Gemini and ChatGPT-4 potentially enhance security protocols, vulnerability assessment, and threat identification. Our research highlights the significance of a novel approach that employs LLMs t…

Cosmological multifield emulator
Sambatra Andrianomena, Sultan Hassan, Francisco Villaescusa-Navarro
https://arxiv.org/abs/2402.10997 https://

Cosmological multifield emulator
We demonstrate the use of deep network to learn the distribution of data from state-of-the-art hydrodynamic simulations of the CAMELS project. To this end, we train a generative adversarial network to generate images composed of three different channels that represent gas density (Mgas), neutral hydrogen density (HI), and magnetic field amplitudes (B). We consider an unconstrained model and another scenario where the model is conditioned on the matter density $Ω_{\rm m}$ and the amplitude of d…

"Light Beams" by @… (Jason Ting) is an enchanting exploration of light and colours that might well have been inspired by the light installations of Dan Flavin. The iterations that I like most are the ones with contrasting colour temperatures, and #35 sticks out to me as especially harmonious.
Project link:

Light Beams
Light Beams by Jason Ting. A generative art project of 150 different outputs. Released Mar 22, 2021, 6:00 PM UTC

Long-form music generation with latent diffusion
Zach Evans, Julian D. Parker, CJ Carr, Zack Zukowski, Josiah Taylor, Jordi Pons
https://arxiv.org/abs/2404.10301

Long-form music generation with latent diffusion
Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure. We show that by training a generative model on long temporal contexts it is possible to produce long-form music of up to 4m45s. Our model consists of a diffusion-transformer operating on a highly downsampled continuous latent representation (latent rate of 21.5Hz). It obtains state-of-the-art generations according to metrics o…

tune your ears towards new horizons with last night's frow show on @…, 3 hours of #freeform #radio for uplifting gormandizers, featuring much excellent new music (including

Generative AI in the Construction Industry: A State-of-the-art Analysis
Ridwan Taiwo, Idris Temitope Bello, Sulemana Fatoama Abdulai, Abdul-Mugis Yussif, Babatunde Abiodun Salami, Abdullahi Saka, Tarek Zayed
https://arxiv.org/abs/2402.09939

This https://arxiv.org/abs/2309.06358 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
Robustness in Natural Language Processing continues to be a pertinent issue, where state of the art models under-perform under naturally shifted distributions. In the context of Question Answering, work on domain adaptation methods continues to be a growing body of research. However, very little attention has been given to the notion of domain generalization under natural distribution shifts, where the target domain is unknown. With drastic improvements in the quality and access to generative m…

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
Zhijie Wang, Yuheng Huang, Da Song, Lei Ma, Tianyi Zhang
https://arxiv.org/abs/2403.04014

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
The recent advancements in Generative AI have significantly advanced the field of text-to-image generation. The state-of-the-art text-to-image model, Stable Diffusion, is now capable of synthesizing high-quality images with a strong sense of aesthetics. Crafting text prompts that align with the model's interpretation and the user's intent thus becomes crucial. However, prompting remains challenging for novice users due to the complexity of the stable diffusion model and the non-trivial efforts …

Review of Generative AI Methods in Cybersecurity
Yagmur Yigit, William J Buchanan, Madjid G Tehrani, Leandros Maglaras
https://arxiv.org/abs/2403.08701 htt…

Review of Generative AI Methods in Cybersecurity
Large language models (LLMs) and generative artificial intelligence (GenAI) constitute paradigm shifts in cybersecurity that present hitherto unseen challenges as well as opportunities. In examining the state-of-the-art application of GenAI in cybersecurity, this work highlights how models like Google's Gemini and ChatGPT-4 potentially enhance security protocols, vulnerability assessment, and threat identification. Our research highlights the significance of a novel approach that employs LLMs t…

Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Foundation Models
Philipp Hess, Michael Aich, Baoxiang Pan, Niklas Boers
https://arxiv.org/abs/2403.02774

Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Foundation Models
Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive. Recent machine learning approaches have shown promising results in downscaling ESM simulations, outperforming state-of-the-art statistical approaches. However, existing methods require computationally costly retraining for each ESM and extrapolate poorly to climates unseen during training. We a…

There’s a neat new core library in CircuitPython: `bitmapfilter`. Originally designed for the PyCamera project, it’s got many useful operations for generative art stuff like I do in Processing/p5js. Here’s a start: random circles bluring away. note, it does require a fast processor like the ESP32-S3 as on this great Lilygo board. Code:

starting to play with bitmapfilter in CircuitPython for Processing- / p5js-like effects
starting to play with bitmapfilter in CircuitPython for Processing- / p5js-like effects - bitmapfilter_play1_code.py

There’s a neat new core library in CircuitPython: `bitmapfilter`. Originally designed for the PyCamera project, it’s got many useful operations for generative art stuff like I do in Processing/p5js. Here’s a start: random circles bluring away. note, it does require a fast processor like the ESP32-S3 as on this great Lilygo board. Code:

Near-perfect Coverage Manifold Estimation in Cellular Networks via conditional GAN
Washim Uddin Mondal, Veni Goyal, Satish V. Ukkusuri, Goutam Das, Di Wang, Mohamed-Slim Alouini, Vaneet Aggarwal
https://arxiv.org/abs/2402.06901

Near-perfect Coverage Manifold Estimation in Cellular Networks via conditional GAN
This paper presents a conditional generative adversarial network (cGAN) that translates base station location (BSL) information of any Region-of-Interest (RoI) to location-dependent coverage probability values within a subset of that region, called the region-of-evaluation (RoE). We train our network utilizing the BSL data of India, the USA, Germany, and Brazil. In comparison to the state-of-the-art convolutional neural networks (CNNs), our model improves the prediction error ($L_1$ difference …

The images of "Aithérios" by @… can appear to show a lift or a fall, can be sparsely populated or tightly packed, but they all convey a sense of translucent weightlessness. Iteration #260 feels special to me in the way it highlights two of its elements in bright white.
Project link:

This https://arxiv.org/abs/2305.18231 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

High-Fidelity Image Compression with Score-based Generative Models
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by…

MagicClay: Sculpting Meshes With Generative Neural Fields
Amir Barda, Vladimir G. Kim, Noam Aigerman, Amit H. Bermano, Thibault Groueix
https://arxiv.org/abs/2403.02460

MagicClay: Sculpting Meshes With Generative Neural Fields
The recent developments in neural fields have brought phenomenal capabilities to the field of shape generation, but they lack crucial properties, such as incremental control - a fundamental requirement for artistic work. Triangular meshes, on the other hand, are the representation of choice for most geometry related tasks, offering efficiency and intuitive control, but do not lend themselves to neural optimization. To support downstream tasks, previous art typically proposes a two-step approach…

This https://arxiv.org/abs/2403.06307 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Fast-Track of F-18 Positron paths simulations
In recent years, the use of Monte Carlo (MC) simulations in the domain of Medical Physics has become a state-of-the-art technology that consumes lots of computational resources for the accurate prediction of particle interactions. The use of generative adversarial network (GAN) has been recently proposed as an alternative to improve the efficiency and extending the applications of computational tools in both medical imaging and therapeutic applications. This study introduces a new approach to s…

This https://arxiv.org/abs/2404.02929 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Using Large Language Models to Understand Telecom Standards
The Third Generation Partnership Project (3GPP) has successfully introduced standards for global mobility. However, the volume and complexity of these standards has increased over time, thus complicating access to relevant information for vendors and service providers. Use of Generative Artificial Intelligence (AI) and in particular Large Language Models (LLMs), may provide faster access to relevant information. In this paper, we evaluate the capability of state-of-art LLMs to be used as Questi…

Measuring Geographic Diversity of Foundation Models with a Natural Language--based Geo-guessing Experiment on GPT-4
Zilong Liu, Krzysztof Janowicz, Kitty Currier, Meilin Shi
https://arxiv.org/abs/2404.07612

Measuring Geographic Diversity of Foundation Models with a Natural Language--based Geo-guessing Experiment on GPT-4
Generative AI based on foundation models provides a first glimpse into the world represented by machines trained on vast amounts of multimodal data ingested by these models during training. If we consider the resulting models as knowledge bases in their own right, this may open up new avenues for understanding places through the lens of machines. In this work, we adopt this thinking and select GPT-4, a state-of-the-art representative in the family of multimodal large language models, to study i…

This https://arxiv.org/abs/2303.01734 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

AdvART: Adversarial Art for Camouflaged Object Detection Attacks
Physical adversarial attacks pose a significant practical threat as it deceives deep learning systems operating in the real world by producing prominent and maliciously designed physical perturbations. Emphasizing the evaluation of naturalness is crucial in such attacks, as humans can readily detect and eliminate unnatural manipulations. To overcome this limitation, recent work has proposed leveraging generative adversarial networks (GANs) to generate naturalistic patches, which may not catch h…

This https://arxiv.org/abs/2305.18231 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

High-Fidelity Image Compression with Score-based Generative Models
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by…

Revisiting an old unfinished project with new eyes & new colors...
#ThingUmbrella #Generative #NoAI #Art

Semi-Supervised Diffusion Model for Brain Age Prediction
Ayodeji Ijishakin, Sophie Martin, Florence Townend, Federica Agosta, Edoardo Gioele Spinelli, Silvia Basaia, Paride Schito, Yuri Falzone, Massimo Filippi, James Cole, Andrea Malaspina
https://arxiv.org/abs/2402.09137

Semi-Supervised Diffusion Model for Brain Age Prediction
Brain age prediction models have succeeded in predicting clinical outcomes in neurodegenerative diseases, but can struggle with tasks involving faster progressing diseases and low quality data. To enhance their performance, we employ a semi-supervised diffusion model, obtaining a 0.83(p<0.01) correlation between chronological and predicted age on low quality T1w MR images. This was competitive with state-of-the-art non-generative methods. Furthermore, the predictions produced by our model were …

Fast-Track of F-18 Positron paths simulations
Youness Mellak, Konstantinos Chatzipapas, Alexandre Bousse, Catherine Chez-Le Rest, Dimitris Visvikis, Julien Bert
https://arxiv.org/abs/2403.06307

Fast-Track of F-18 Positron paths simulations
In recent years, the use of Monte Carlo (MC) simulations in the domain of Medical Physics has become a state-of-the-art technology that consumes lots of computational resources for the accurate prediction of particle interactions. The use of generative adversarial network (GAN) has been recently proposed as an alternative to improve the efficiency and extending the applications of computational tools in both medical imaging and therapeutic applications. This study introduces a new approach to s…