Tootfinder

Better headline: “Farage boot licker uses stolen data via generative AI to resurrect man who shot his pet cats in a drug-fueled rage”
https://www.stereogum.com/2317966/rod-stewart-ozzy-osbourne-ai-video-tribute/news/

(Yet another) 1-minute excerpt of an #Umbra variation, one of my recent algorithmic/generative realtime animation art pieces, constantly evolving and exhibited exclusively on Layer.
Very much love this color theme, especially after ~15 seconds... 🤌
(See above hashtag for other clips)
Made with ❤️ and my opensource

"How a Teaching-Focused Institution Approaches AI Literacy"
https://katinamagazine.org/content/article/future-of-work/2025/ai-literacy-at-a-teaching-focused-institution
"At the Institute of Inner-City …

What's Behind the Magic? Audiences Seek Artistic Value in Generative AI's Contributions to a Live Dance Performance
Jacqueline Elise Bruen, Myounghoon Jeon
https://arxiv.org/abs/2508.00239

What's Behind the Magic? Audiences Seek Artistic Value in Generative AI's Contributions to a Live Dance Performance
With the development of generative artificial intelligence (GenAI) tools to create art, stakeholders cannot come to an agreement on the value of these works. In this study we uncovered the mixed opinions surrounding art made by AI. We developed two versions of a dance performance augmented by technology either with or without GenAI. For each version we informed audiences of the performance's development either before or after a survey on their perceptions of the performance. There were thirty-n…

Better Call Claude: Can LLMs Detect Changes of Writing Style?
Johannes R\"omisch, Svetlana Gorovaia, Mariia Halchynska, Gleb Schmidt, Ivan P. Yamshchikov
https://arxiv.org/abs/2508.00680

Better Call Claude: Can LLMs Detect Changes of Writing Style?
This article explores the zero-shot performance of state-of-the-art large language models (LLMs) on one of the most challenging tasks in authorship analysis: sentence-level style change detection. Benchmarking four LLMs on the official PAN~2024 and 2025 "Multi-Author Writing Style Analysis" datasets, we present several observations. First, state-of-the-art generative models are sensitive to variations in writing style - even at the granular level of individual sentences. Second, their accuracy …

MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
Berker Demirel, Marco Fumero, Theofanis Karaletsos, Francesco Locatello
https://arxiv.org/abs/2510.01298

MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
Simulating in silico cellular responses to interventions is a promising direction to accelerate high-content image-based assays, critical for advancing drug discovery and gene editing. To support this, we introduce MorphGen, a state-of-the-art diffusion-based generative model for fluorescent microscopy that enables controllable generation across multiple cell types and perturbations. To capture biologically meaningful patterns consistent with known cellular morphologies, MorphGen is trained wit…

Another 1-minute excerpt of an #Umbra variation, one of my recent algorithmic/generative realtime animation art pieces, constantly evolving and exhibited exclusively on Layer.
(See above hashtag for other clips)
Made with ❤️ and my opensource https://th…

Overclocking Electrostatic Generative Models
Daniil Shlenskii, Alexander Korotin
https://arxiv.org/abs/2509.22454 https://arxiv.org/pdf/2509.22454

Overclocking Electrostatic Generative Models
Electrostatic generative models such as PFGM++ have recently emerged as a powerful framework, achieving state-of-the-art performance in image synthesis. PFGM++ operates in an extended data space with auxiliary dimensionality $D$, recovering the diffusion model framework as $D\to\infty$, while yielding superior empirical results for finite $D$. Like diffusion models, PFGM++ relies on expensive ODE simulations to generate samples, making it computationally costly. To address this, we propose Inve…

Distribution estimation via Flow Matching with Lipschitz guarantees
Lea Kunkel
https://arxiv.org/abs/2509.02337 https://arxiv.org/pdf/2509.02337

Distribution estimation via Flow Matching with Lipschitz guarantees
Flow Matching, a promising approach in generative modeling, has recently gained popularity. Relying on ordinary differential equations, it offers a simple and flexible alternative to diffusion models, which are currently the state-of-the-art. Despite its empirical success, the mathematical understanding of its statistical power so far is very limited. This is largely due to the sensitivity of theoretical bounds to the Lipschitz constant of the vector field which drives the ODE. In this work, we…

More releases today: New version of https://thi.ng/genart-api, an art-platform-independent API for browser-based generative art.
The new version (v0.28.0) addresses some recent (type) changes in TypeScript and updates the WebAssembly bindings to support the latest Zig 0.15.1 (just like releases of some of my o…

thi.ng/genart-api

🍮 Wissen zum Nachtisch: 🍨
Immer mehr Menschen sehen sich im beruflichen Umfeld genötigt, mit generativer #KI zu arbeiten.
Besonders Großunternehmen „überrollen“ damit ihre #Mitarbeiter. Es wird eine Art

Generative KI für Einsteiger - Praxisnahe Prompts für Privat und Beruf – einfach erklärt
Buchempfehlungen zu Klimawandel, Nachhaltigkeit, Umweltschutz und Klimaanpassung

If you get an invite to this generative art software engineering call, note that if you submit something and it gets accepted, as far as I can tell it would cost you $3000 in open access fees... unless you want it to languish behind a paywall (you'd then only be allowed to share an unedited draft, and even then would have to advertise the paywall on it). They don't seem to want to make this clear in their call.

Exploring Opportunities to Support Novice Visual Artists' Inspiration and Ideation with Generative AI
Cindy Peng, Alice Qian, Linghao Jin, Jieneng Chen, Evans Xu Han, Paul Pu Liang, Hong Shen, Haiyi Zhu, Jane Hsieh
https://arxiv.org/abs/2509.24167

Exploring Opportunities to Support Novice Visual Artists' Inspiration and Ideation with Generative AI
Recent generative AI advances present new possibilities for supporting visual art creation, but how such promise might assist novice artists during early-stage processes requires investigation. How novices adopt or resist these tools can shift the relationship between the art community and generative systems. We interviewed 13 artists to uncover needs in key dimensions during early stages of creation: (1) quicker and better access to references, (2) visualizations of reference combinations, (3)…

Bias beyond Borders: Global Inequalities in AI-Generated Music
Ahmet Solak, Florian Gr\"otschla, Luca A. Lanzend\"orfer, Roger Wattenhofer
https://arxiv.org/abs/2510.01963

Bias beyond Borders: Global Inequalities in AI-Generated Music
While recent years have seen remarkable progress in music generation models, research on their biases across countries, languages, cultures, and musical genres remains underexplored. This gap is compounded by the lack of datasets and benchmarks that capture the global diversity of music. To address these challenges, we introduce GlobalDISCO, a large-scale dataset consisting of 73k music tracks generated by state-of-the-art commercial generative music models, along with paired links to 93k refer…

R doesnt need to be a hard and scientific tool 📈. You can use it to make art 🎨: #rstats

GitHub - cutterkom/generativeart: Create Generative Art with R
Create Generative Art with R. Contribute to cutterkom/generativeart development by creating an account on GitHub.

Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
Kai Goebel, Patrik Zips
https://arxiv.org/abs/2507.23589 https://arxiv.org/pdf/2507.…

Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
Recent advancements in Large Language Models have sparked interest in their potential for robotic task planning. While these models demonstrate strong generative capabilities, their effectiveness in producing structured and executable plans remains uncertain. This paper presents a systematic evaluation of a broad spectrum of current state of the art language models, each directly prompted using Planning Domain Definition Language domain and problem files, and compares their planning performance…

Transport Based Mean Flows for Generative Modeling
Elaheh Akbari, Ping He, Ahmadreza Moradipari, Yikun Bai, Soheil Kolouri
https://arxiv.org/abs/2509.22592 https://

Transport Based Mean Flows for Generative Modeling
Flow-matching generative models have emerged as a powerful paradigm for continuous data generation, achieving state-of-the-art results across domains such as images, 3D shapes, and point clouds. Despite their success, these models suffer from slow inference due to the requirement of numerous sequential sampling steps. Recent work has sought to accelerate inference by reducing the number of sampling steps. In particular, Mean Flows offer a one-step generation approach that delivers substantial s…

Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Art
Dayu Fan, Rui Meng, Xiaodong Xu, Yiming Liu, Guoshun Nan, Chenyuan Feng, Shujun Han, Song Gao, Bingxuan Xu, Dusit Niyato, Tony Q. S. Quek, Ping Zhang
https://arxiv.org/abs/2507.16733

Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Art
With the rapid development of Generative Artificial Intelligence (GAI) technology, Generative Diffusion Models (GDMs) have shown significant empowerment potential in the field of wireless networks due to advantages, such as noise resistance, training stability, controllability, and multimodal generation. Although there have been multiple studies focusing on GDMs for wireless networks, there is still a lack of comprehensive reviews on their technological evolution. Motivated by this, we systemat…

Aesthetic Experience and Educational Value in Co-creating Art with Generative AI: Evidence from a Survey of Young Learners
Chengyuan Zhang, Suzhe Xu
https://arxiv.org/abs/2509.10576

Aesthetic Experience and Educational Value in Co-creating Art with Generative AI: Evidence from a Survey of Young Learners
This study investigates the aesthetic experience and educational value of collaborative artmaking with generative artificial intelligence (AI) among young learners and art students. Based on a survey of 112 participants, we examine how human creators renegotiate their roles, how conventional notions of originality are challenged, how the creative process is transformed, and how aesthetic judgment is formed in human--AI co-creation. Empirically, participants generally view AI as a partner that s…

🍮 Wissen zum Nachtisch: 🍨
Immer mehr Menschen sehen sich im beruflichen Umfeld genötigt, mit generativer #KI zu arbeiten.
Besonders Großunternehmen „überrollen“ damit ihre #Mitarbeiter. Es wird eine Art

Generative KI für Einsteiger - Praxisnahe Prompts für Privat und Beruf – einfach erklärt
Buchempfehlungen zu Klimawandel, Nachhaltigkeit, Umweltschutz und Klimaanpassung

Remagine Ventures: 342 Israeli startups are focused on generative AI in 2025, up by 198 since May 2024, and they have collectively raised $20B to date (Elihay Vidal/CTech)
https://www.calcalistech.com/ctechnews/article/s1yl6mlulx

Mapping Israel’s $20B GenAI boom: 342 startups and counting
New Remagine Ventures report charts explosive growth and the rise of agentic AI systems.

Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement
Shrishti Saha Shetu, Emanu\"el A. P. Habets, Andreas Brendel
https://arxiv.org/abs/2508.20859

Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement
Generative speech enhancement methods based on generative adversarial networks (GANs) and diffusion models have shown promising results in various speech enhancement tasks. However, their performance in very low signal-to-noise ratio (SNR) scenarios remains under-explored and limited, as these conditions pose significant challenges to both discriminative and generative state-of-the-art methods. To address this, we propose a method that leverages latent features extracted from discriminative spe…

FuXi-TC: A generative framework integrating deep learning and physics-based models for improved tropical cyclone forecasts
Shan Guo, Lei Chen, Zeyi Niu, Ziyao Sun, Xinyan Zhang, Yangyang Zhao, Xiaohui Zhong, Hao Li
https://arxiv.org/abs/2508.16168

FuXi-TC: A generative framework integrating deep learning and physics-based models for improved tropical cyclone forecasts
Tropical cyclones (TCs) are among the most devastating natural hazards, yet their intensity remains notoriously difficult to predict. Numerical weather prediction (NWP) models are constrained by both computational demands and intrinsic predictability, while state-of-the-art deep learning-based weather forecasting models tend to underestimate TC intensity due to biases in reanalysis-based training data. Here, we present FuXi-TC, a diffusion-based generative forecasting framework that combines th…

Been working on some additions/adjustments for #Umbra, one of my recent algorithmic/generative art pieces, currently shown exclusively on Layer.
Here's a 3 minute segment (of an infinite realtime animation). Give it time to develop/change! Fullscreen playback probably best...
Made with

A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
Behnoud Shafiezadeh, Amir Mashmool, Farshad Eshghi, Manoochehr Kelarestaghi
https://arxiv.org/abs/2509.06868

A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
Automatic License-Plate Recognition (ALPR) plays a pivotal role in Intelligent Transportation Systems (ITS) as a fundamental element of Smart Cities. However, due to its high variability, ALPR faces challenging issues more efficiently addressed by deep learning techniques. In this paper, a selective Generative Adversarial Network (GAN) is proposed for deblurring in the preprocessing step, coupled with the state-of-the-art You-Only-Look-Once (YOLO)v5 object detection architectures for License-Pl…

🍮 Wissen zum Nachtisch: 🍨
Immer mehr Menschen sehen sich im beruflichen Umfeld genötigt, mit generativer #KI zu arbeiten.
Besonders Großunternehmen „überrollen“ damit ihre #Mitarbeiter. Es wird eine Art

Generative KI für Einsteiger - Praxisnahe Prompts für Privat und Beruf – einfach erklärt
Buchempfehlungen zu Klimawandel, Nachhaltigkeit, Umweltschutz und Klimaanpassung

An effective potential for generative modelling with active matter
Adrian Baule
https://arxiv.org/abs/2508.08146 https://arxiv.org/pdf/2508.08146

An effective potential for generative modelling with active matter
Score-based diffusion models generate samples from a complex underlying data distribution by time-reversal of a diffusion process and represent the state-of-the-art in many generative AI applications such as artificial image synthesis. Here, I show how a generative diffusion model can be implemented based on an underlying active particle process with finite correlation time. In contrast to previous approaches that use a score function acting on the velocity coordinate of the active particle, ti…

Siracusa@mastodon.social It looks like the BBC is using AI to generate its own headlines now … Looks https://www.bbc.co.uk/mediacentre/2025/articles/bbc-to-launch-new-generative-ai-pilots-to-support-news-production/

BBC to launch new Generative AI pilots to support news production

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code
Nenad Petrovic, Vahid Zolfaghari, Andre Schamschurko, Sven Kirchner, Fengjunjie Pan, Chengdng Wu, Nils Purschke, Aleksei Velsh, Krzysztof Lebioda, Yinglei Song, Yi Zhang, Lukasz Mazur, Alois Knoll
https://arxiv.org/abs/2507.15025

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code
Adoption of state-of-art Generative Artificial Intelligence (GenAI) aims to revolutionize many industrial areas by reducing the amount of human intervention needed and effort for handling complex underlying processes. Automotive software development is considered to be a significant area for GenAI adoption, taking into account lengthy and expensive procedures, resulting from the amount of requirements and strict standardization. In this paper, we explore the adoption of GenAI for various steps …

SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
Yi Guo, Wei Wang, Zhihang Yuan, Rong Cao, Kuan Chen, Zhengyang Chen, Yuanyuan Huo, Yang Zhang, Yuping Wang, Shouda Liu, Yuxuan Wang
https://arxiv.org/abs/2507.16884

SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
Generative models like Flow Matching have achieved state-of-the-art performance but are often hindered by a computationally expensive iterative sampling process. To address this, recent work has focused on few-step or one-step generation by learning the average velocity field, which directly maps noise to data. MeanFlow, a leading method in this area, learns this field by enforcing a differential identity that connects the average and instantaneous velocities. In this work, we argue that this d…

Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training
Naisong Zhou, Saisamarth Rajesh Phaye, Milos Cernak, Tijana Stojkovic, Andy Pearce, Andrea Cavallaro, Andy Harper
https://arxiv.org/abs/2509.21522

Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training
Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Neural Function Evaluations (NFEs), posing a challenge for real-time applications. On the contrary, flow matching offers a more efficient alternative by learning a direct vector field, enabling high-quality synthesis in just a few steps using deterministic ordinary differential equation~(ODE) solvers. We thus introduce …

Flexibility-Conditioned Protein Structure Design with Flow Matching
Vsevolod Viliuga, Leif Seute, Nicolas Wolf, Simon Wagner, Arne Elofsson, Jan St\"uhmer, Frauke Gr\"ater
https://arxiv.org/abs/2508.18211

Flexibility-Conditioned Protein Structure Design with Flow Matching
Recent advances in geometric deep learning and generative modeling have enabled the design of novel proteins with a wide range of desired properties. However, current state-of-the-art approaches are typically restricted to generating proteins with only static target properties, such as motifs and symmetries. In this work, we take a step towards overcoming this limitation by proposing a framework to condition structure generation on flexibility, which is crucial for key functionalities such as c…

The Ethical Implications of AI in Creative Industries: A Focus on AI-Generated Art
Prerana Khatiwada, Joshua Washington, Tyler Walsh, Ahmed Saif Hamed, Lokesh Bhatta
https://arxiv.org/abs/2507.05549

The Ethical Implications of AI in Creative Industries: A Focus on AI-Generated Art
As Artificial Intelligence (AI) continues to grow daily, more exciting (and somewhat controversial) technology emerges every other day. As we see the advancements in AI, we see more and more people becoming skeptical of it. This paper explores the complications and confusion around the ethics of generative AI art. We delve deep into the ethical side of AI, specifically generative art. We step back from the excitement and observe the impossible conundrums that this impressive technology produces…

DiffQ: Unified Parameter Initialization for Variational Quantum Algorithms via Diffusion Models
Chi Zhang, Mengxin Zheng, Qian Lou, Fan Chen
https://arxiv.org/abs/2509.17324 htt…

DiffQ: Unified Parameter Initialization for Variational Quantum Algorithms via Diffusion Models
Variational Quantum Algorithms (VQAs) are widely used in the noisy intermediate-scale quantum (NISQ) era, but their trainability and performance depend critically on initialization parameters that shape the optimization landscape. Existing machine learning-based initializers achieve state-of-the-art results yet remain constrained to single-task domains and small datasets of only hundreds of samples. We address these limitations by reformulating VQA parameter initialization as a generative model…

DLSF: Dual-Layer Synergistic Fusion for High-Fidelity Image Syn-thesis
Zhen-Qi Chen, Yuan-Fu Yang
https://arxiv.org/abs/2507.13388 https://

DLSF: Dual-Layer Synergistic Fusion for High-Fidelity Image Syn-thesis
With the rapid advancement of diffusion-based generative models, Stable Diffusion (SD) has emerged as a state-of-the-art framework for high-fidelity im-age synthesis. However, existing SD models suffer from suboptimal feature aggregation, leading to in-complete semantic alignment and loss of fine-grained details, especially in highly textured and complex scenes. To address these limitations, we propose a novel dual-latent integration framework that en-hances feature interactions between the bas…

The Impact of Artificial Intelligence on Traditional Art Forms: A Disruption or Enhancement
Viswa Chaitanya Marella, Sai Teja Erukude, Suhasnadh Reddy Veluru
https://arxiv.org/abs/2509.07029

The Impact of Artificial Intelligence on Traditional Art Forms: A Disruption or Enhancement
The introduction of Artificial Intelligence (AI) into the domains of traditional art (visual arts, performing arts, and crafts) has sparked a complicated discussion about whether this might be an agent of disruption or an enhancement of our traditional art forms. This paper looks at the duality of AI, exploring the ways that recent technologies like Generative Adversarial Networks and Diffusion Models, and text-to-image generators are changing the fields of painting, sculpture, calligraphy, dan…

Saddle Hierarchy in Dense Associative Memory
Robin Th\'eriault, Daniele Tantari
https://arxiv.org/abs/2508.19151 https://arxiv.org/pdf/2508.19151

Saddle Hierarchy in Dense Associative Memory
Dense associative memory (DAM) models have been attracting renewed attention since they were shown to be robust to adversarial examples and closely related to state-of-the-art machine learning paradigms, such as the attention mechanisms in transformers and generative diffusion models. We study a DAM built upon a three-layer Boltzmann machine with Potts hidden units, which represent data clusters and classes. Through a statistical mechanics analysis, we derive saddle-point equations that charact…

Machine Learning Assisted Parameter-Space Searches for Lensed Gravitational Waves
Giulia Campailla, Marco Raveri, Wayne Hu, Jose Mar\'ia Ezquiaga
https://arxiv.org/abs/2509.06901

Machine Learning Assisted Parameter-Space Searches for Lensed Gravitational Waves
When a gravitational wave encounters a massive object along the line of sight, repeated copies of the original signal may be produced due to gravitational lensing. In this paper, we develop a series of new machine-learning based statistical methods to identify promising strong lensing candidates in gravitational wave catalogs. We employ state-of-the-art normalizing flow generative models to perform statistical calculations on the posterior distributions of gravitational wave events that would o…

KDPE: A Kernel Density Estimation Strategy for Diffusion Policy Trajectory Selection
Andrea Rosasco, Federico Ceola, Giulia Pasquale, Lorenzo Natale
https://arxiv.org/abs/2508.10511

KDPE: A Kernel Density Estimation Strategy for Diffusion Policy Trajectory Selection
Learning robot policies that capture multimodality in the training data has been a long-standing open challenge for behavior cloning. Recent approaches tackle the problem by modeling the conditional action distribution with generative models. One of these approaches is Diffusion Policy, which relies on a diffusion model to denoise random points into robot action trajectories. While achieving state-of-the-art performance, it has two main drawbacks that may lead the robot out of the data distribu…

Discrete Diffusion Models for Language Generation
Ashen Weligalle
https://arxiv.org/abs/2507.07050 https://arxiv.org/pdf/2507.07050…

Discrete Diffusion Models for Language Generation
Diffusion models have emerged as a powerful class of generative models, achieving state-of-the-art results in continuous data domains such as image and video generation. Their core mechanism involves a forward diffusion process that gradually transforms structured data into a Gaussian-like distribution, followed by a learned reverse process to reconstruct the data. While successful in continuous modalities, applying this framework to discrete data-particularly natural language-remains challengi…

Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation
Jessup Byun, Xiaofeng Lin, Joshua Ward, Guang Cheng
https://arxiv.org/abs/2507.17066

Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation
Synthetic tabular data is essential for machine learning workflows, especially for expanding small or imbalanced datasets and enabling privacy-preserving data sharing. However, state-of-the-art generative models (GANs, VAEs, diffusion models) rely on large datasets with thousands of examples. In low-data settings, often the primary motivation for synthetic data, these models can overfit, leak sensitive records, and require frequent retraining. Recent work uses large pre-trained transformers to …

Say It, See It: A Systematic Evaluation on Speech-Based 3D Content Generation Methods in Augmented Reality
Yanming Xiu, Joshua Chilukuri, Shunav Sen, Maria Gorlatova
https://arxiv.org/abs/2508.12498

Say It, See It: A Systematic Evaluation on Speech-Based 3D Content Generation Methods in Augmented Reality
As augmented reality (AR) applications increasingly require 3D content, generative pipelines driven by natural input such as speech offer an alternative to manual asset creation. In this work, we design a modular, edge-assisted architecture that supports both direct text-to-3D and text-image-to-3D pathways, enabling interchangeable integration of state-of-the-art components and systematic comparison of their performance in AR settings. Using this architecture, we implement and evaluate four rep…

Attentive AV-FusionNet: Audio-Visual Quality Prediction with Hybrid Attention
Ina Salaj, Arijit Biswas
https://arxiv.org/abs/2509.16994 https://arxiv.org/p…

Attentive AV-FusionNet: Audio-Visual Quality Prediction with Hybrid Attention
We introduce a novel deep learning-based audio-visual quality (AVQ) prediction model that leverages internal features from state-of-the-art unimodal predictors. Unlike prior approaches that rely on simple fusion strategies, our model employs a hybrid representation that combines learned Generative Machine Listener (GML) audio features with hand-crafted Video Multimethod Assessment Fusion (VMAF) video features. Attention mechanisms capture cross-modal interactions and intra-modal relationships, …

Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study
Kutub Uddin, Muhammad Umar Farooq, Awais Khan, Khalid Mahmood Malik
https://arxiv.org/abs/2509.07132

Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study
The widespread use of generative AI has shown remarkable success in producing highly realistic deepfakes, posing a serious threat to various voice biometric applications, including speaker verification, voice biometrics, audio conferencing, and criminal investigations. To counteract this, several state-of-the-art (SoTA) audio deepfake detection (ADD) methods have been proposed to identify generative AI signatures to distinguish between real and deepfake audio. However, the effectiveness of thes…

Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation
Thanh Nguyen, Chang D. Yoo
https://arxiv.org/abs/2508.13904 https://

Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation
The generative power of diffusion models (DMs) has recently enabled high-performing decision-making algorithms in offline reinforcement learning (RL), achieving state-of-the-art results across standard benchmarks. Among them, Diffusion Q-Learning (DQL) stands out as a leading method for its consistently strong performance. Nevertheless, DQL remains limited in practice due to its reliance on multi-step denoising for action generation during both training and inference. Although one-step denoisin…

Verified Language Processing with Hybrid Explainability: A Technical Report
Oliver Robert Fox, Giacomo Bergami, Graham Morgan
https://arxiv.org/abs/2507.05017

Verified Language Processing with Hybrid Explainability: A Technical Report
The volume and diversity of digital information have led to a growing reliance on Machine Learning techniques, such as Natural Language Processing, for interpreting and accessing appropriate data. While vector and graph embeddings represent data for similarity tasks, current state-of-the-art pipelines lack guaranteed explainability, failing to determine similarity for given full texts accurately. These considerations can also be applied to classifiers exploiting generative language models with …

Testing chatbots on the creation of encoders for audio conditioned image generation
Jorge E. Le\'on, Miguel Carrasco
https://arxiv.org/abs/2509.09717 https://

Testing chatbots on the creation of encoders for audio conditioned image generation
On one hand, recent advances in chatbots has led to a rising popularity in using these models for coding tasks. On the other hand, modern generative image models primarily rely on text encoders to translate semantic concepts into visual representations, even when there is clear evidence that audio can be employed as input as well. Given the previous, in this work, we explore whether state-of-the-art conversational agents can design effective audio encoders to replace the CLIP text encoder from …

Teaching Sustainable Creative Technologies
Chelsea Thompto
https://arxiv.org/abs/2507.05320 https://arxiv.org/pdf/2507.05320

Teaching Sustainable Creative Technologies
Artists and especially new media artists contribute to public perceptions and adoption of new technologies through their own use of emerging media technologies such as augmented and virtual reality, generative image systems, and high-resolution displays in the production of their work. In this way, art and media production can be understood as part of the larger issue of unsustainable computational consumption. As such, it is critical for artists to develop, share, and promote new and more sust…

DiffRhythm : Controllable and Flexible Full-Length Song Generation with Preference Optimization
Huakang Chen, Yuepeng Jiang, Guobin Ma, Chunbo Hao, Shuai Wang, Jixun Yao, Ziqian Ning, Meng Meng, Jian Luan, Lei Xie
https://arxiv.org/abs/2507.12890

DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization
Songs, as a central form of musical art, exemplify the richness of human intelligence and creativity. While recent advances in generative modeling have enabled notable progress in long-form song generation, current systems for full-length song synthesis still face major challenges, including data imbalance, insufficient controllability, and inconsistent musical quality. DiffRhythm, a pioneering diffusion-based model, advanced the field by generating full-length songs with expressive vocals and …

Uncertainty-Aware Tabular Prediction: Evaluating VBLL-Enhanced TabPFN in Safety-Critical Medical Data
Madhushan Ramalingam
https://arxiv.org/abs/2509.10048 https://

Uncertainty-Aware Tabular Prediction: Evaluating VBLL-Enhanced TabPFN in Safety-Critical Medical Data
Predictive models are being increasingly used across a wide range of domains, including safety-critical applications such as medical diagnosis and criminal justice. Reliable uncertainty estimation is a crucial task in such settings. Tabular Prior-data Fitted Network (TabPFN) is a recently proposed machine learning foundation model for tabular dataset, which uses a generative transformer architecture. Variational Bayesian Last Layers (VBLL) is a state-of-the-art lightweight variational formulati…