Tootfinder

Humanoid World Models: Open World Foundation Models for Humanoid Robotics
Muhammad Qasim Ali, Aditya Sridhar, Shahbuland Matiana, Alex Wong, Mohammad Al-Sharman
https://arxiv.org/abs/2506.01182

Humanoid World Models: Open World Foundation Models for Humanoid Robotics
Humanoid robots have the potential to perform complex tasks in human centered environments but require robust predictive models to reason about the outcomes of their actions. We introduce Humanoid World Models (HWM) a family of lightweight open source video based models that forecast future egocentric observations conditioned on actions. We train two types of generative models Masked Transformers and FlowMatching on 100 hours of humanoid demonstrations. Additionally we explore architectural var…

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
Krishna Acharya, Aleksandr V. Petrov, Juba Ziani
https://arxiv.org/abs/2506.01910

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
We propose Generative Low-rank language model with Semantic Search (GLoSS), a generative recommendation framework that combines large language models with dense retrieval for sequential recommendation. Unlike prior methods such as GPT4Rec, which rely on lexical matching via BM25, GLoSS uses semantic search to retrieve relevant items beyond lexical matching. For query generation, we employ 4-bit quantized LlaMA-3 models fine-tuned with low-rank adaptation (LoRA), enabling efficient training and …

Frontiers of Generative AI for Network Optimization: Theories, Limits, and Visions
Bo Yang, Ruihuai Liang, Weixin Li, Han Wang, Xuelin Cao, Zhiwen Yu, Samson Lasaulce, M\'erouane Debbah, Mohamed-Slim Alouini, H. Vincent Poor, Chau Yuen
https://arxiv.org/abs/2507.01773

Frontiers of Generative AI for Network Optimization: Theories, Limits, and Visions
While interest in the application of generative AI (GenAI) in network optimization has surged in recent years, its rapid progress has often overshadowed critical limitations intrinsic to generative models that remain insufficiently examined in existing literature. This survey provides a comprehensive review and critical analysis of GenAI in network optimization. We focus on the two dominant paradigms of GenAI including generative diffusion models (GDMs) and large pre-trained models (LPTMs), and…

A Quantum Information Theoretic Approach to Tractable Probabilistic Models
Pedro Zuidberg Dos Martires
https://arxiv.org/abs/2506.01824 https://

A Quantum Information Theoretic Approach to Tractable Probabilistic Models
By recursively nesting sums and products, probabilistic circuits have emerged in recent years as an attractive class of generative models as they enjoy, for instance, polytime marginalization of random variables. In this work we study these machine learning models using the framework of quantum information theory, leading to the introduction of positive unital circuits (PUnCs), which generalize circuit evaluations over positive real-valued probabilities to circuit evaluations over positive semi…

Few-step Adversarial Schr\"{o}dinger Bridge for Generative Speech Enhancement
Seungu Han, Sungho Lee, Juheon Lee, Kyogu Lee
https://arxiv.org/abs/2506.01460

Few-step Adversarial Schrödinger Bridge for Generative Speech Enhancement
Deep generative models have recently been employed for speech enhancement to generate perceptually valid clean speech on large-scale datasets. Several diffusion models have been proposed, and more recently, a tractable Schrödinger Bridge has been introduced to transport between the clean and noisy speech distributions. However, these models often suffer from an iterative reverse process and require a large number of sampling steps -- more than 50. Our investigation reveals that the performance…

AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models
Anthony M. Barrett, Jessica Newman, Brandie Nonnecke, Nada Madkour, Dan Hendrycks, Evan R. Murphy, Krystal Jackson, Deepika Raman
https://arxiv.org/abs/2506.23949

AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models
Increasingly multi-purpose AI models, such as cutting-edge large language models or other 'general-purpose AI' (GPAI) models, 'foundation models,' generative AI models, and 'frontier models' (typically all referred to hereafter with the umbrella term 'GPAI/foundation models' except where greater specificity is needed), can provide many beneficial capabilities but also risks of adverse events with profound consequences. This document provides risk-management practices or controls for identifying…

Machine vs Machine: Using AI to Tackle Generative AI Threats in Assessment
Mohammad Saleh Torkestani, Taha Mansouri
https://arxiv.org/abs/2506.02046 https:…

Machine vs Machine: Using AI to Tackle Generative AI Threats in Assessment
This paper presents a theoretical framework for addressing the challenges posed by generative artificial intelligence (AI) in higher education assessment through a machine-versus-machine approach. Large language models like GPT-4, Claude, and Llama increasingly demonstrate the ability to produce sophisticated academic content, traditional assessment methods face an existential threat, with surveys indicating 74-92% of students experimenting with these tools for academic purposes. Current respon…

An Exploratory Framework for Future SETI Applications: Detecting Generative Reactivity via Language Models
Po-Chieh Yu
#toXiv_bot_toot

Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
Arkaprabha Ganguli, Nesar Ramachandra, Julie Bessac, Emil Constantinescu
https://arxiv.org/abs/2507.00298

Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
This study addresses the challenge of statistically extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings. We investigate encoder-decoder-based generative models for nonlinear dimensionality reduction, focusing on disentangling low-dimensional latent variables corresponding to independent physical factors. Introducing Aux-VAE, a novel architecture within the classical Variational Autoencoder framework, we achieve disentanglement with m…

Physics-based Generative Models for Geometrically Consistent and Interpretable Wireless Channel Synthesis
Satyavrat Wagle, Akshay Malhotra, Shahab Hamidi-Rad, Aditya Sant, David J. Love, Christopher G. Brinton
https://arxiv.org/abs/2506.00374

Physics-based Generative Models for Geometrically Consistent and Interpretable Wireless Channel Synthesis
In recent years, machine learning (ML) methods have become increasingly popular in wireless communication systems for several applications. A critical bottleneck for designing ML systems for wireless communications is the availability of realistic wireless channel datasets, which are extremely resource-intensive to produce. To this end, the generation of realistic wireless channels plays a key role in the subsequent design of effective ML algorithms for wireless communication systems. Generativ…

Benchmarking Large Language Models for Polymer Property Predictions
Sonakshi Gupta, Akhlak Mahmood, Shivank Shukla, Rampi Ramprasad
https://arxiv.org/abs/2506.02129

Benchmarking Large Language Models for Polymer Property Predictions
Machine learning has revolutionized polymer science by enabling rapid property prediction and generative design. Large language models (LLMs) offer further opportunities in polymer informatics by simplifying workflows that traditionally rely on large labeled datasets, handcrafted representations, and complex feature engineering. LLMs leverage natural language inputs through transfer learning, eliminating the need for explicit fingerprinting and streamlining training. In this study, we finetune …

Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs
Francesco Di Salvo, Hanh Huyen My Nguyen, Christian Ledig
https://arxiv.org/abs/2507.02671

Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs
Deep Learning (DL) has revolutionized medical imaging, yet its adoption is constrained by data scarcity and privacy regulations, limiting access to diverse datasets. Federated Learning (FL) enables decentralized training but suffers from high communication costs and is often restricted to a single downstream task, reducing flexibility. We propose a data-sharing method via Differentially Private (DP) generative models. By adopting foundation models, we extract compact, informative embeddings, re…

MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
Liancheng Fang, Aiwei Liu, Henry Peng Zou, Yankai Chen, Hengrui Zhang, Zhongfen Deng, Philip S. Yu
https://arxiv.org/abs/2505.24267

MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer invertibility compared to other modalities, compromising performance. Simultaneously, tabular diffusion models require substantially less computation than other modalities, enabling a multi-sample selection approach to tabular generative model watermarking. MUSE embeds…

Semantics-Guided Generative Image Compression
Cheng-Lin Wu, Hyomin Choi, Ivan V. Baji\'c
https://arxiv.org/abs/2505.24015 https://

Semantics-Guided Generative Image Compression
Advancements in text-to-image generative AI with large multimodal models are spreading into the field of image compression, creating high-quality representation of images at extremely low bit rates. This work introduces novel components to the existing multimodal image semantic compression (MISC) approach, enhancing the quality of the generated images in terms of PSNR and perceptual metrics. The new components include semantic segmentation guidance for the generative decoder, as well as content…

GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion
Sunkyung Lee, Minjin Choi, Eunseong Choi, Hye-young Kim, Jongwuk Lee
https://arxiv.org/abs/2506.01673

GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion
Generative recommendation is an emerging paradigm that leverages the extensive knowledge of large language models by formulating recommendations into a text-to-text generation task. However, existing studies face two key limitations in (i) incorporating implicit item relationships and (ii) utilizing rich yet lengthy item information. To address these challenges, we propose a Generative Recommender via semantic-Aware Multi-granular late fusion (GRAM), introducing two synergistic innovations. Fir…

This https://arxiv.org/abs/2503.17770 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Probabilistic Net Load Forecasting for High-Penetration RES Grids Utilizing Enhanced Conditional Diffusion Model
The proliferation of intermittent distributed renewable energy sources (RES) in modern power systems has fundamentally compromised the reliability and accuracy of deterministic net load forecasting. Generative models, particularly diffusion models, demonstrate exceptional potential in uncertainty quantification for scenario forecasting. Nevertheless, their probabilistic predictive capabilities and conditional bootstrapping mechanisms still remain underexplored. In this paper, a day-ahead probab…

UniConFlow: A Unified Constrained Generalization Framework for Certified Motion Planning with Flow Matching Models
Zewen Yang, Xiaobing Dai, Dian Yu, Qianru Li, Yu Li, Valentin Le Mesle
https://arxiv.org/abs/2506.02955

UniConFlow: A Unified Constrained Generalization Framework for Certified Motion Planning with Flow Matching Models
Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of constraints, such as collision avoidance and dynamic consistency, which are often treated separately or only partially considered. This paper proposes UniConFlow, a unified flow matching (FM) based framework for trajectory generation that systematically incorp…

Getting More from Less: Transfer Learning Improves Sleep Stage Decoding Accuracy in Peripheral Wearable Devices
William G Coon, Diego Luna, Akshita Panagrahi, Matthew Reid, Mattson Ogg
https://arxiv.org/abs/2506.00730

Getting More from Less: Transfer Learning Improves Sleep Stage Decoding Accuracy in Peripheral Wearable Devices
Transfer learning, a technique commonly used in generative artificial intelligence, allows neural network models to bring prior knowledge to bear when learning a new task. This study demonstrates that transfer learning significantly enhances the accuracy of sleep-stage decoding from peripheral wearable devices by leveraging neural network models pretrained on electroencephalographic (EEG) signals. Consumer wearable technologies typically rely on peripheral physiological signals such as pulse pl…

Using Diffusion Models to do Data Assimilation
Daniel Hodyss, Matthias Morzfeld
https://arxiv.org/abs/2506.02249 https://arxiv.org/pd…

Using Diffusion Models to do Data Assimilation
The recent surge in machine learning (ML) methods for geophysical modeling has raised the question of how these same ML methods might be applied to data assimilation (DA). We focus on diffusion modeling (a form of generative artificial intelligence) and on systems that can perform the entire DA, rather than on ML-based tools that are used within an otherwise conventional DA system. We explain that there are (at least) three different types of diffusion-based DA systems and we show in detail tha…

Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
Anantha Narayanan Suresh Babu, Akhil Sadam, Pierre F. J. Lermusiaux
https://arxiv.org/abs/2507.00719

Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
Typically, numerical simulations of the ocean, weather, and climate are coarse, and observations are sparse and gappy. In this work, we apply four generative diffusion modeling approaches to super-resolution and inference of forced two-dimensional quasi-geostrophic turbulence on the beta-plane from coarse, sparse, and gappy observations. Two guided approaches minimally adapt a pre-trained unconditional model: SDEdit modifies the initial condition, and Diffusion Posterior Sampling (DPS) modifies…

Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency
Bunlong Lay, Rostilav Makarov, Timo Gerkmann
https://arxiv.org/abs/2506.02908

Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency
Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing streaming data in real-time. In this work, we adapt a sliding window diffusion framework to the speech enhancement task. Our approach progressively corrupts speech signals through time, assigning more noise to frames close to the present in a buffer. This approach …

Solving inverse problems of Type IIB flux vacua with conditional generative models
Sven Krippendorf, Zhimei Liu
https://arxiv.org/abs/2506.22551 https://…

Solving inverse problems of Type IIB flux vacua with conditional generative models
We address the inverse problem in Type IIB flux compactifications of identifying flux vacua with targeted phenomenological properties such as specific superpotential values or tadpole constraints using conditional generative models. These machine learning techniques overcome computational bottlenecks in traditional approaches such as rejection sampling and Markov Chain Monte Carlo (MCMC), which struggle to generate rare, finely-tuned vacua. As a proof of concept, we demonstrate that conditional…

Email as the Interface to Generative AI Models: Seamless Administrative Automation
Andres Navarro, Carlos de Quinto, Jos\'e Alberto Hern\'andez
https://arxiv.org/abs/2506.23850

Email as the Interface to Generative AI Models: Seamless Administrative Automation
This paper introduces a novel architectural framework that integrates Large Language Models (LLMs) with email interfaces to automate administrative tasks, specifically targeting accessibility barriers in enterprise environments. The system connects email communication channels with Optical Character Recognition (OCR) and intelligent automation, enabling non-technical administrative staff to delegate complex form-filling and document processing tasks using familiar email interfaces. By treating …

This https://arxiv.org/abs/2310.17451 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings
Making neural visual generative models controllable by logical reasoning systems is promising for improving faithfulness, transparency, and generalizability. We propose the Abductive visual Generation (AbdGen) approach to build such logic-integrated models. A vector-quantized symbol grounding mechanism and the corresponding disentanglement training method are introduced to enhance the controllability of logical symbols over generation. Furthermore, we propose two logical abduction methods to ma…

SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations
Zhican Wang, Guanghui He, Hongxiang Fan
https://arxiv.org/abs/2507.01309

SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations
The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image generation and a foundation for next-generation multi-modal algorithms. However, its high computational and memory demands hinder inference speed and energy efficiency. To address these challenges, we identify three core issues: (1) intensive and often redund…

Cross-Modal Characterization of Thin Film MoS$_2$ Using Generative Models
Isaiah A. Moses, Chen Chen, Joan M. Redwing, Wesley F. Reinhart
https://arxiv.org/abs/2505.24065

Cross-Modal Characterization of Thin Film MoS$_2$ Using Generative Models
The growth and characterization of materials using empirical optimization typically requires a significant amount of expert time, experience, and resources. Several complementary characterization methods are routinely performed to determine the quality and properties of a grown sample. Machine learning (ML) can support the conventional approaches by using historical data to guide and provide speed and efficiency to the growth and characterization of materials. Specifically, ML can provide quant…

MVGBench: Comprehensive Benchmark for Multi-view Generation Models
Xianghui Xie, Chuhang Zou, Meher Gitika Karumuri, Jan Eric Lenssen, Gerard Pons-Moll
https://arxiv.org/abs/2507.00006

MVGBench: Comprehensive Benchmark for Multi-view Generation Models
We propose MVGBench, a comprehensive benchmark for multi-view image generation models (MVGs) that evaluates 3D consistency in geometry and texture, image quality, and semantics (using vision language models). Recently, MVGs have been the main driving force in 3D object creation. However, existing metrics compare generated images against ground truth target views, which is not suitable for generative tasks where multiple solutions exist while differing from ground truth. Furthermore, different M…

ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization
Pengyu Ren, Wenhao Guan, Kaidi Wang, Peijie Chen, Qingyang Hong, Lin Li
https://arxiv.org/abs/2506.01032

ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization
In recent years, diffusion-based generative models have demonstrated remarkable performance in speech conversion, including Denoising Diffusion Probabilistic Models (DDPM) and others. However, the advantages of these models come at the cost of requiring a large number of sampling steps. This limitation hinders their practical application in real-world scenarios. In this paper, we introduce ReFlow-VC, a novel high-fidelity speech conversion method based on rectified flow. Specifically, ReFlow-VC…

DiffPINN: Generative diffusion-initialized physics-informed neural networks for accelerating seismic wavefield representation
Shijun Cheng, Tariq Alkhalifah
https://arxiv.org/abs/2506.00471

DiffPINN: Generative diffusion-initialized physics-informed neural networks for accelerating seismic wavefield representation
Physics-informed neural networks (PINNs) offer a powerful framework for seismic wavefield modeling, yet they typically require time-consuming retraining when applied to different velocity models. Moreover, their training can suffer from slow convergence due to the complexity of of the wavefield solution. To address these challenges, we introduce a latent diffusion-based strategy for rapid and effective PINN initialization. First, we train multiple PINNs to represent frequency-domain scattered w…

This https://arxiv.org/abs/2412.04339 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Likelihood-Scheduled Score-Based Generative Modeling for Fully 3D PET Image Reconstruction
Medical image reconstruction with pre-trained score-based generative models (SGMs) has advantages over other existing state-of-the-art deep-learned reconstruction methods, including improved resilience to different scanner setups and advanced image distribution modeling. SGM-based reconstruction has recently been applied to simulated positron emission tomography (PET) datasets, showing improved contrast recovery for out-of-distribution lesions relative to the state-of-the-art. However, existing…

Why AI can't possibly make you more productive; long
#AI and "productivity", some thoughts:
Productivity is a concept that isn't entirely meaningless outside the context of capitalism, but it's a concept that is heavily inflected in a capitalist context. In many uses today it effectively means "how much you can satisfy and/or exceed your boss' expectations." This is not really what it should mean: even in an anarchist utopia, people would care about things like how many shirts they can produce in a week, although in an "I'd like to voluntarily help more people" way rather than an "I need to meet this quota to earn my survival" way. But let's roll with this definition for a second, because it's almost certainly what your boss means when they say "productivity", and understanding that word in a different (even if truer) sense is therefore inherently dangerous.
Accepting "productivity" to mean "satisfying your boss' expectations," I will now claim: the use of generative AI cannot increase your productivity.
Before I dive in, it's imperative to note that the big generative models which most people think of as constituting "AI" today are evil. They are 1: pouring fuel on our burning planet, 2: psychologically strip-mining a class of data laborers who are exploited for their precarity, 3: enclosing, exploiting, and polluting the digital commons, and 4: stealing labor from broad classes of people many of whom are otherwise glad to give that labor away for free provided they get a simple acknowledgement in return. Any of these four "ethical issues" should be enough *alone* to cause everyone to simply not use the technology. These ethical issues are the reason that I do not use generative AI right now, except for in extremely extenuating circumstances. These issues are also convincing for a wide range of people I talk to, from experts to those with no computer science background. So before I launch into a critique of the effectiveness of generative AI, I want to emphasize that such a critique should be entirely unnecessary.
But back to my thesis: generative AI cannot increase your productivity, where "productivity" has been defined as "how much you can satisfy and/or exceed your boss' expectations."
Why? In fact, what the fuck? Every AI booster I've met has claimed the opposite. They've given me personal examples of time saved by using generative AI. Some of them even truly believe this. Sometimes I even believe they saved time without horribly compromising on quality (and often, your boss doesn't care about quality anyways if the lack of quality is hard to measure of doesn't seem likely to impact short-term sales/feedback/revenue). So if generative AI genuinely lets you write more emails in a shorter period of time, or close more tickets, or something else along these lines, how can I say it isn't increasing your ability to meet your boss' expectations?
The problem is simple: your boss' expectations are not a fixed target. Never have been. In virtue of being someone who oversees and pays wages to others under capitalism, your boss' game has always been: pay you less than the worth of your labor, so that they can accumulate profit and this more capital to remain in charge instead of being forced into working for a wage themselves. Sure, there are layers of manservant caught in between who aren't fully in this mode, but they are irrelevant to this analysis. It matters not how much you please your manager if your CEO thinks your work is not worth the wages you are being paid. And using AI actively lowers the value of your work relative to your wages.
Why do I say that? It's actually true in several ways. The most obvious: using generative AI lowers the quality of your work, because the work it produces is shot through with errors, and when your job is reduced to proofreading slop, you are bound to tire a bit, relax your diligence, and let some mistakes through. More than you would have if you are actually doing and taking pride in the work. Examples are innumerable and frequent, from journalists to lawyers to programmers, and we laugh at them "haha how stupid to not check whether the books the AI reviewed for you actually existed!" but on a deeper level if we're honest we know we'd eventually make the same mistake ourselves (bonus game: spot the swipe-typing typos I missed in this post; I'm sure there will be some).
But using generative AI also lowers the value of your work in another much more frightening way: in this era of hype, it demonstrates to your boss that you could be replaced by AI. The more you use it, and no matter how much you can see that your human skills are really necessary to correct its mistakes, the more it appears to your boss that they should hire the AI instead of you. Or perhaps retain 10% of the people in roles like yours to manage the AI doing the other 90% of the work. Paradoxically, the *more* you get done in terms of raw output using generative AI, the more it looks to your boss as if there's an opportunity to get enough work done with even fewer expensive humans. Of course, the decision to fire you and lean more heavily into AI isn't really a good one for long-term profits and success, but the modern boss did not get where they are by considering long-term profits. By using AI, you are merely demonstrating your redundancy, and the more you get done with it, the more redundant you seem.
In fact, there's even a third dimension to this: by using generative AI, you're also providing its purveyors with invaluable training data that allows them to make it better at replacing you. It's generally quite shitty right now, but the more use it gets by competent & clever people, the better it can become at the tasks those specific people use it for. Using the currently-popular algorithm family, there are limits to this; I'm not saying it will eventually transcend the mediocrity it's entwined with. But it can absolutely go from underwhelmingly mediocre to almost-reasonably mediocre with the right training data, and data from prompting sessions is both rarer and more useful than the base datasets it's built on.
For all of these reasons, using generative AI in your job is a mistake that will likely lead to your future unemployment. To reiterate, you should already not be using it because it is evil and causes specific and inexcusable harms, but in case like so many you just don't care about those harms, I've just explained to you why for entirely selfish reasons you should not use it.
If you're in a position where your boss is forcing you to use it, my condolences. I suggest leaning into its failures instead of trying to get the most out of it, and as much as possible, showing your boss very clearly how it wastes your time and makes things slower. Also, point out the dangers of legal liability for its mistakes, and make sure your boss is aware of the degree to which any of your AI-eager coworkers are producing low-quality work that harms organizational goals.
Also, if you've read this far and aren't yet of an anarchist mindset, I encourage you to think about the implications of firing 75% of (at least the white-collar) workforce in order to make more profit while fueling the climate crisis and in most cases also propping up dictatorial figureheads in government. When *either* the AI bubble bursts *or* if the techbros get to live out the beginnings of their worker-replacement fantasies, there are going to be an unimaginable number of economically desperate people living in increasingly expensive times. I'm the kind of optimist who thinks that the resulting social crucible, though perhaps through terrible violence, will lead to deep social changes that effectively unseat from power the ultra-rich that continue to drag us all down this destructive path, and I think its worth some thinking now about what you might want the succeeding stable social configuration to look like so you can advocate towards that during points of malleability.
As others have said more eloquently, generative AI *should* be a technology that makes human lives on average easier, and it would be were it developed & controlled by humanists. The only reason that it's not, is that it's developed and controlled by terrible greedy people who use their unfairly hoarded wealth to immiserate the rest of us in order to maintain their dominance. In the long run, for our very survival, we need to depose them, and I look forward to what the term "generative AI" will mean after that finally happens.

Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach
Hao Wei, Wanli Ni, Wen Wang, Wenjun Xu, Dusit Niyato, Ping Zhang
https://arxiv.org/abs/2507.01728

Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach
This letter proposes UniToCom, a unified token communication paradigm that treats tokens as the fundamental units for both processing and wireless transmission. Specifically, to enable efficient token representations, we propose a generative information bottleneck (GenIB) principle, which facilitates the learning of tokens that preserve essential information while supporting reliable generation across multiple modalities. By doing this, GenIB-based tokenization is conducive to improving the com…

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data
Yan Zhou, Bradley Malin, Murat Kantarcioglu
https://arxiv.org/abs/2506.01907 https://

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data
Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not without its own challenges. Synthetic data produced by generative models trained on source data may inadvertently reveal information about outliers. Techniques specifically designed for preserving privacy, such as introducing noise to satisfy differential priva…

This https://arxiv.org/abs/2505.07802 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Improving Trajectory Stitching with Flow Models
Generative models have shown great promise as trajectory planners, given their affinity to modeling complex distributions and guidable inference process. Previous works have successfully applied these in the context of robotic manipulation but perform poorly when the required solution does not exist as a complete trajectory within the training set. We identify that this is a result of being unable to plan via stitching, and subsequently address the architectural and dataset choices needed to re…

TeamCMU at Touch\'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search
To Eun Kim, Jo\~ao Coelho, Gbemileke Onilude, Jai Singh
https://arxiv.org/abs/2507.00509

TeamCMU at Touché: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search
As conversational search engines increasingly adopt generation-based paradigms powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), the integration of advertisements into generated responses presents both commercial opportunities and challenges for user experience. Unlike traditional search, where advertisements are clearly delineated, generative systems blur the boundary between informational content and promotional material, raising concerns around transparency an…

Graph Representation-based Model Poisoning on Federated LLMs in CyberEdge Networks
Hanlin Cai, Haofan Dong, Houtianfu Wang, Kai Li, Ozgur B. Akan
https://arxiv.org/abs/2507.01694 …

Graph Representation-based Model Poisoning on Federated LLMs in CyberEdge Networks
Federated large language models (FedLLMs) provide powerful generative capabilities in CyberEdge networks while protecting data privacy. However, FedLLMs remains highly vulnerable to model poisoning attacks. This article first reviews recent model poisoning techniques and existing defense mechanisms for FedLLMs, highlighting critical limitations, particularly under non-IID text distributions. In particular, current defenses primarily utilize distance-based outlier detection or norm constraints, …

Integrating Universal Generative AI Platforms in Educational Labs to Foster Critical Thinking and Digital Literacy
Vasiliy Znamenskiy, Rafael Niyazov, Joel Hernandez
https://arxiv.org/abs/2507.00007

Integrating Universal Generative AI Platforms in Educational Labs to Foster Critical Thinking and Digital Literacy
This paper presents a new educational framework for integrating generative artificial intelligence (GenAI) platforms such as ChatGPT, Claude, and Gemini into laboratory activities aimed at developing critical thinking and digital literacy among undergraduate students. Recognizing the limitations and risks of uncritical reliance on large language models (LLMs), the proposed pedagogical model reframes GenAI as a research subject and cognitive tool. Students formulate discipline-specific prompts a…

Crowdsourcing MUSHRA Tests in the Age of Generative Speech Technologies: A Comparative Analysis of Subjective and Objective Testing Methods
Laura Lechler, Chamran Moradi, Ivana Balic
https://arxiv.org/abs/2506.00950

Crowdsourcing MUSHRA Tests in the Age of Generative Speech Technologies: A Comparative Analysis of Subjective and Objective Testing Methods
The MUSHRA framework is widely used for detecting subtle audio quality differences but traditionally relies on expert listeners in controlled environments, making it costly and impractical for model development. As a result, objective metrics are often used during development, with expert evaluations conducted later. While effective for traditional DSP codecs, these metrics often fail to reliably evaluate generative models. This paper proposes adaptations for conducting MUSHRA tests with non-ex…

University of Chicago Becker-Friedman Institute of Economics just published research this April 2025 of how Generative AI has had "almost no significant wage or labor impact so far".
✅ Large Language Models, Small Labor Market Effects
https://papers.ssrn.com/sol3/papers.cf

This https://arxiv.org/abs/2502.03498 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
Generating street-view images from satellite imagery is a challenging task, particularly in maintaining accurate pose alignment and incorporating diverse environmental conditions. While diffusion models have shown promise in generative tasks, their ability to maintain strict pose alignment throughout the diffusion process is limited. In this paper, we propose a novel Iterative Homography Adjustment (IHA) scheme applied during the denoising process, which effectively addresses pose misalignment …

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity
Jacopo Nudo, Mario Edoardo Pandolfo, Edoardo Loru, Mattia Samory, Matteo Cinelli, Walter Quattrociocchi
https://arxiv.org/abs/2507.00657

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity
We investigate how Large Language Models (LLMs) behave when simulating political discourse on social media. Leveraging 21 million interactions on X during the 2024 U.S. presidential election, we construct LLM agents based on 1,186 real users, prompting them to reply to politically salient tweets under controlled conditions. Agents are initialized either with minimal ideological cues (Zero Shot) or recent tweet history (Few Shot), allowing one-to-one comparisons with human replies. We evaluate t…

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge
Nabarun Goswami, Tatsuya Harada
https://arxiv.org/abs/2506.00809

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge
We propose a multi-stage framework for universal speech enhancement, designed for the Interspeech 2025 URGENT Challenge. Our system first employs a Sparse Compression Network to robustly separate sources and extract an initial clean speech estimate from noisy inputs. This is followed by an efficient generative model that refines speech quality by leveraging self-supervised features and optimizing a masked language modeling objective on acoustic tokens derived from a neural audio codec. In the f…

This https://arxiv.org/abs/2307.14634 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Fact-Checking of AI-Generated Reports
With advances in generative artificial intelligence (AI), it is now possible to produce realistic-looking automated reports for preliminary reads of radiology images. This can expedite clinical workflows, improve accuracy and reduce overall costs. However, it is also well-known that such models often hallucinate, leading to false findings in the generated reports. In this paper, we propose a new method of fact-checking of AI-generated reports using their associated images. Specifically, the dev…

This https://arxiv.org/abs/2505.16499 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Smaller, Smarter, Closer: The Edge of Collaborative Generative AI
The rapid adoption of generative AI (GenAI), particularly Large Language Models (LLMs), has exposed critical limitations of cloud-centric deployments, including latency, cost, and privacy concerns. Meanwhile, Small Language Models (SLMs) are emerging as viable alternatives for resource-constrained edge environments, though they often lack the capabilities of their larger counterparts. This article explores the potential of collaborative inference systems that leverage both edge and cloud resour…

Imitation Learning for Satellite Attitude Control under Unknown Perturbations
Zhizhuo Zhang, Hao Peng, Xiaoli Bai
https://arxiv.org/abs/2507.01161 https://…

Imitation Learning for Satellite Attitude Control under Unknown Perturbations
This paper presents a novel satellite attitude control framework that integrates Soft Actor-Critic (SAC) reinforcement learning with Generative Adversarial Imitation Learning (GAIL) to achieve robust performance under various unknown perturbations. Traditional control techniques often rely on precise system models and are sensitive to parameter uncertainties and external perturbations. To overcome these limitations, we first develop a SAC-based expert controller that demonstrates improved resil…

Innovative Research on IoT Architecture and Robotic Operating Platforms: Applications of Large Language Models and Generative AI
Huiwen Han
https://arxiv.org/abs/2506.22477

Innovative Research on IoT Architecture and Robotic Operating Platforms: Applications of Large Language Models and Generative AI
This paper introduces an innovative design for robotic operating platforms, underpinned by a transformative Internet of Things (IoT) architecture, seamlessly integrating cutting-edge technologies such as large language models (LLMs), generative AI, edge computing, and 5G networks. The proposed platform aims to elevate the intelligence and autonomy of IoT systems and robotics, enabling them to make real-time decisions and adapt dynamically to changing environments. Through a series of compelling…

Hierarchical Intention-Aware Expressive Motion Generation for Humanoid Robots
Lingfan Bao, Yan Pan, Tianhu Peng, Chengxu Zhou
https://arxiv.org/abs/2506.01563

Hierarchical Intention-Aware Expressive Motion Generation for Humanoid Robots
Effective human-robot interaction requires robots to identify human intentions and generate expressive, socially appropriate motions in real-time. Existing approaches often rely on fixed motion libraries or computationally expensive generative models. We propose a hierarchical framework that combines intention-aware reasoning via in-context learning (ICL) with real-time motion generation using diffusion models. Our system introduces structured prompting with confidence scoring, fallback behavio…

Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion Framework
Semih Kacmaz, E. A. Huerta, Roland Haas
https://arxiv.org/abs/2507.02106 ht…

Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion Framework
We present a hybrid machine learning framework that combines Physics-Informed Neural Operators (PINOs) with score-based generative diffusion models to simulate the full spatio-temporal evolution of two-dimensional, incompressible, resistive magnetohydrodynamic (MHD) turbulence across a broad range of Reynolds numbers ($\mathrm{Re}$). The framework leverages the equation-constrained generalization capabilities of PINOs to predict coherent, low-frequency dynamics, while a conditional diffusion mo…

This https://arxiv.org/abs/2411.14681 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model
Multimodal diffusion models for image editing generate outputs conditioned on both textual instructions and visual inputs, aiming to modify target regions while preserving the rest of the image. Although diffusion models have been shown to be vulnerable to backdoor attacks, existing efforts mainly focus on unimodal generative models and fail to address the unique challenges in multimodal image editing. In this paper, we present the first study of backdoor attacks on multimodal diffusion-based i…

Historical Contingencies Steer the Topology of Randomly Assembled Graphs
Cole Mathis, Harrison B. Smith
https://arxiv.org/abs/2507.00335 https://

Historical Contingencies Steer the Topology of Randomly Assembled Graphs
Graphs are used to represent and analyze data in domains as diverse as physics, biology, chemistry, planetary science, and the social sciences. Across domains, random graph models relate generative processes to expected graph properties, and allow for sampling from distinct ensembles. Here we introduce a new random graph model, inspired by assembly theory, and characterize the graphs it generates. We show that graphs generated using our method represent a diverse ensemble, characterized by a br…

Generative Social Choice: The Next Generation
Niclas Boehmer, Sara Fish, Ariel D. Procaccia
https://arxiv.org/abs/2505.22939 https://…

Generative Social Choice: The Next Generation
A key task in certain democratic processes is to produce a concise slate of statements that proportionally represents the full spectrum of user opinions. This task is similar to committee elections, but unlike traditional settings, the candidate set comprises all possible statements of varying lengths, and so it can only be accessed through specific queries. Combining social choice and large language models, prior work has approached this challenge through a framework of generative social choic…

Teaching Programming in the Age of Generative AI: Insights from Literature, Pedagogical Proposals, and Student Perspectives
Clemente Rubio-Manzano, Jazna Meza, Rodolfo Fernandez-Santibanez, Christian Vidal-Castro
https://arxiv.org/abs/2507.00108

Teaching Programming in the Age of Generative AI: Insights from Literature, Pedagogical Proposals, and Student Perspectives
Computer programming is undergoing a true transformation driven by powerful new tools for automatic source code generation based on large language models. This transformation is also manifesting in introductory programming courses at universities around the world, generating an in-depth debate about how programming content should be taught, learned, and assessed in the context of generative artificial intelligence. This article aims, on the one hand, to review the most relevant studies on thi…

Aligning Protein Conformation Ensemble Generation with Physical Feedback
Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Aur\'elie Lozano, Vijil Chenthamarakshan, Payel Das, Jian Tang
https://arxiv.org/abs/2505.24203

Aligning Protein Conformation Ensemble Generation with Physical Feedback
Protein dynamics play a crucial role in protein biological functions and properties, and their traditional study typically relies on time-consuming molecular dynamics (MD) simulations conducted in silico. Recent advances in generative modeling, particularly denoising diffusion models, have enabled efficient accurate protein structure prediction and conformation sampling by learning distributions over crystallographic structures. However, effectively integrating physical supervision into these d…

PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
Mert Kiray, Paul Uhlenbruck, Nassir Navab, Benjamin Busam
https://arxiv.org/abs/2506.01091

PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
Visual effects (VFX) are key to immersion in modern films, games, and AR/VR. Creating 3D effects requires specialized expertise and training in 3D animation software and can be time consuming. Generative solutions typically rely on computationally intense methods such as diffusion models which can be slow at 4D inference. We reformulate 3D animation as a field prediction task and introduce a text-driven framework that infers a time-varying 4D flow field acting on 3D Gaussians. By leveraging lar…

This https://arxiv.org/abs/2505.19314 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
Target Speech Extraction (TSE) aims to isolate a target speaker's voice from a mixture of multiple speakers by leveraging speaker-specific cues, typically provided as auxiliary audio (a.k.a. cue audio). Although recent advancements in TSE have primarily employed discriminative models that offer high perceptual quality, these models often introduce unwanted artifacts, reduce naturalness, and are sensitive to discrepancies between training and testing environments. On the other hand, generative m…

Regularity of the score function in generative models
Arthur St\'ephanovitch
https://arxiv.org/abs/2506.19559 https://arxiv.org/p…

Regularity of the score function in generative models
We study the regularity of the score function in score-based generative models and show that it naturally adapts to the smoothness of the data distribution. Under minimal assumptions, we establish Lipschitz estimates that directly support convergence and stability analyses in both diffusion and ODE-based generative models. In addition, we derive higher-order regularity bounds, which simplify existing arguments for optimally approximating the score function using neural networks.

This https://arxiv.org/abs/2504.10545 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

HSTU-BLaIR: Lightweight Contrastive Text Embedding for Generative Recommender
Recent advances in recommender systems have underscored the complementary strengths of generative modeling and pretrained language models. We propose HSTU-BLaIR, a hybrid framework that augments the Hierarchical Sequential Transduction Unit (HSTU)-based generative recommender with BLaIR, a lightweight contrastive text embedding model. This integration enriches item representations with semantic signals from textual metadata while preserving HSTU's powerful sequence modeling capabilities. We e…

DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains
Yongkang Xiao, Sinian Zhang, Yi Dai, Huixue Zhou, Jue Hou, Jie Ding, Rui Zhang
https://arxiv.org/abs/2506.00708

DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains
Knowledge graph completion (KGC) aims to predict missing triples in knowledge graphs (KGs) by leveraging existing triples and textual information. Recently, generative large language models (LLMs) have been increasingly employed for graph tasks. However, current approaches typically encode graph context in textual form, which fails to fully exploit the potential of LLMs for perceiving and reasoning about graph structures. To address this limitation, we propose DrKGC (Dynamic Subgraph Retrieval-…

This https://arxiv.org/abs/2502.03498 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
Generating street-view images from satellite imagery is a challenging task, particularly in maintaining accurate pose alignment and incorporating diverse environmental conditions. While diffusion models have shown promise in generative tasks, their ability to maintain strict pose alignment throughout the diffusion process is limited. In this paper, we propose a novel Iterative Homography Adjustment (IHA) scheme applied during the denoising process, which effectively addresses pose misalignment …

SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
Weiliang Chen, Jiayi Bi, Yuanhui Huang, Wenzhao Zheng, Yueqi Duan
https://arxiv.org/abs/2506.10981

SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
Generative models have gained significant attention in novel view synthesis (NVS) by alleviating the reliance on dense multi-view captures. However, existing methods typically fall into a conventional paradigm, where generative models first complete missing areas in 2D, followed by 3D recovery techniques to reconstruct the scene, which often results in overly smooth surfaces and distorted geometry, as generative models struggle to infer 3D structure solely from RGB data. In this paper, we propo…

CaloHadronic: a diffusion model for the generation of hadronic showers
Thorsten Buss, Frank Gaede, Gregor Kasieczka, Anatolii Korol, Katja Kr\"uger, Peter McKeown, Martina Mozzanica
https://arxiv.org/abs/2506.21720

CaloHadronic: a diffusion model for the generation of hadronic showers
Simulating showers of particles in highly-granular calorimeters is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models can enable them to augment traditional simulations and alleviate a major computing constraint. Recent developments have shown how diffusion based generative shower simulation approaches that do not rely on a fixed structure, but instead generate geometry-independent point clouds, ar…

Adobe releases iOS and Android apps for Firefly, letting users generate images and videos using text prompts and experiment with popular AI photo editing tools (Jess Weatherbed/The Verge)
https://www.theverge.com/news/688080/adobe-firefly-…

Adobe made a mobile app for its Firefly generative AI tools
The all-in-one platform for Adobe’s Firefly generative AI models is now available on iPhone and Android devices.

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
Stanley Wu, Ronik Bhaskar, Anna Yoo Jeong Ha, Shawn Shan, Haitao Zheng, Ben Y. Zhao
https://arxiv.org/abs/2506.21874

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying the models with large volumes of high-quality image-caption pairs during training. However, recent work suggests that VLMs are vulnerable to stealthy adversarial attacks, where adversarial perturbations are added to images to mislead the VLMs into producing …

MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation
Yakun Song, Jiawei Chen, Xiaobin Zhuang, Chenpeng Du, Ziyang Ma, Jian Wu, Jian Cong, Dongya Jia, Zhuo Chen, Yuping Wang, Yuxuan Wang, Xie Chen
https://arxiv.org/abs/2506.00385

MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation
Neural audio codecs have made significant strides in efficiently mapping raw audio waveforms into discrete token representations, which are foundational for contemporary audio generative models. However, most existing codecs are optimized primarily for reconstruction quality, often at the expense of the downstream modelability of the encoded tokens. Motivated by the need to overcome this bottleneck, we introduce $\textbf{MagiCodec}$, a novel single-layer, streaming Transformer-based audio codec…

Adapting University Policies for Generative AI: Opportunities, Challenges, and Policy Solutions in Higher Education
Russell Beale
https://arxiv.org/abs/2506.22231

Adapting University Policies for Generative AI: Opportunities, Challenges, and Policy Solutions in Higher Education
The rapid proliferation of generative artificial intelligence (AI) tools - especially large language models (LLMs) such as ChatGPT - has ushered in a transformative era in higher education. Universities in developed regions are increasingly integrating these technologies into research, teaching, and assessment. On one hand, LLMs can enhance productivity by streamlining literature reviews, facilitating idea generation, assisting with coding and data analysis, and even supporting grant proposal d…

Red Teaming for Generative AI, Report on a Copyright-Focused Exercise Completed in an Academic Medical Center
James Wen, Sahil Nalawade, Zhiwei Liang, Catherine Bielick, Marisa Ferrara Boston, Alexander Chowdhury, Adele Collin, Luigi De Angelis, Jacob Ellen, Heather Frase, Rodrigo R. Gameiro, Juan Manuel Gutierrez, Pooja Kadam, Murat Keceli, Srikanth Krishnamurthy, Anne Kwok, Yanan Lance Lu, Heather Mattie, Liam G. McCoy, Katherine Miller, Allison C. Morgan, Marlene Louisa Moerig, Tran…

Red Teaming for Generative AI, Report on a Copyright-Focused Exercise Completed in an Academic Medical Center
Generative AI is present in multiple industries. Dana-Farber Cancer Institute, in partnership with Microsoft, has created an internal AI tool, GPT4DFCI. Together we hosted a red teaming event to assess whether the underlying GPT models that support the tool would output copyrighted data. Our teams focused on reproducing content from books, news articles, scientific articles, and electronic health records. We found isolated instances where GPT4DFCI was able to identify copyrighted material and r…

GATSim: Urban Mobility Simulation with Generative Agents
Qi Liu, Can Li, Wanjing Ma
https://arxiv.org/abs/2506.23306 https://arxiv.or…

GATSim: Urban Mobility Simulation with Generative Agents
Traditional agent-based urban mobility simulations rely on rigid rule-based systems that fail to capture the complexity, adaptability, and behavioral diversity characteristic of human travel decision-making. Recent advances in large language models and AI agent technology offer opportunities to create agents with reasoning capabilities, persistent memory, and adaptive learning mechanisms. We propose GATSim (Generative-Agent Transport Simulation), a novel framework that leverages these advances …

This https://arxiv.org/abs/2405.02696 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model
Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating potential risks associated with Artificial Intelligence (AI)-generated contents. However, post-processed watermarking methods are unable to withstand generative watermark attacks and there exists a trade-off between image fidelity and watermark strength. There…

DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization
Geonyoung Lee, Geonhee Han, Paul Hongsuck Seo
https://arxiv.org/abs/2506.02858

DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization
Language-queried Audio Source Separation (LASS) enables open-vocabulary sound separation via natural language queries. While existing methods rely on task-specific training, we explore whether pretrained diffusion models, originally designed for audio generation, can inherently perform separation without further training. In this study, we introduce a training-free framework leveraging generative priors for zero-shot LASS. Analyzing naïve adaptations, we identify key limitations arising from m…

MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction
Lingtong Zhang, Mengdie Song, Xiaohan Hao, Huayu Mai, Bensheng Qiu
https://arxiv.org/abs/2506.23701

MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction
Magnetic Resonance Imaging (MRI) reconstruction is essential in medical diagnostics. As the latest generative models, diffusion models (DMs) have struggled to produce high-fidelity images due to their stochastic nature in image domains. Latent diffusion models (LDMs) yield both compact and detailed prior knowledge in latent domains, which could effectively guide the model towards more effective learning of the original data distribution. Inspired by this, we propose Multi-domain Diffusion Prior…

Performance Measurements in the AI-Centric Computing Continuum Systems
Praveen Kumar Donta, Qiyang Zhang, Schahram Dustdar
https://arxiv.org/abs/2506.22884

Performance Measurements in the AI-Centric Computing Continuum Systems
Over the Eight decades, computing paradigms have shifted from large, centralized systems to compact, distributed architectures, leading to the rise of the Distributed Computing Continuum (DCC). In this model, multiple layers such as cloud, edge, Internet of Things (IoT), and mobile platforms work together to support a wide range of applications. Recently, the emergence of Generative AI and large language models has further intensified the demand for computational resources across this continuum…

Critically-Damped Higher-Order Langevin Dynamics
Benjamin Sterling, Chad Gueli, M\'onica F. Bugallo
https://arxiv.org/abs/2506.21741 https://

Critically-Damped Higher-Order Langevin Dynamics
Denoising Diffusion Probabilistic Models represent an entirely new class of generative AI methods that have yet to be fully explored. Critical damping has been successfully introduced in Critically-Damped Langevin Dynamics (CLD) and Critically-Damped Third-Order Langevin Dynamics (TOLD++), but has not yet been applied to dynamics of arbitrary order. The proposed line of work generalizes Higher-Order Langevin Dynamics (HOLD), a recent state-of-the-art diffusion method, by introducing the concept…

A Variational Framework for Improving Naturalness in Generative Spoken Language Models
Li-Wei Chen, Takuya Higuchi, Zakaria Aldeneh, Ahmed Hussen Abdelaziz, Alexander Rudnicky
https://arxiv.org/abs/2506.14767

A Variational Framework for Improving Naturalness in Generative Spoken Language Models
The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized for autoregressive modeling. Speech tokens derived from self-supervised models (known as semantic tokens) typically focus on the linguistic aspects of speech but neglect prosodic information. As a result, models trained on these tokens can generate speech with reduced naturalness. Existing approaches try to fix this by…

XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark
Ioan-Paul Ciobanu, Andrei-Iulian Hiji, Nicolae-Catalin Ristea, Paul Irofti, Cristian Rusu, Radu Tudor Ionescu
https://arxiv.org/abs/2506.00462

XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark
Recent advances in audio generation led to an increasing number of deepfakes, making the general public more vulnerable to financial scams, identity theft, and misinformation. Audio deepfake detectors promise to alleviate this issue, with many recent studies reporting accuracy rates close to 99%. However, these methods are typically tested in an in-domain setup, where the deepfake samples from the training and test sets are produced by the same generative models. To this end, we introduce XMAD-…

Geological Everything Model 3D: A Promptable Foundation Model for Unified and Zero-Shot Subsurface Understanding
Yimin Dou, Xinming Wu, Nathan L Bangs, Harpreet Singh Sethi, Jintao Li, Hang Gao, Zhixiang Guo
https://arxiv.org/abs/2507.00419

Geological Everything Model 3D: A Promptable Foundation Model for Unified and Zero-Shot Subsurface Understanding
Understanding Earth's subsurface is critical for energy transition, natural hazard mitigation, and planetary science. Yet subsurface analysis remains fragmented, with separate models required for structural interpretation, stratigraphic analysis, geobody segmentation, and property modeling-each tightly coupled to specific data distributions and task formulations. We introduce the Geological Everything Model 3D (GEM), a unified generative architecture that reformulates all these tasks as prompt-…

Replaced article(s) found for physics.flu-dyn. https://arxiv.org/list/physics.flu-dyn/new
[1/1]:
- Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
Mohammed Sardar, Alex Skillen, Ma{\l}gorzata J. Zimo\'n, Samuel Draycott, Alistair Re…

Toward the Explainability of Protein Language Models for Sequence Design
Andrea Hunklinger, Noelia Ferruz
https://arxiv.org/abs/2506.19532 https://

Toward the Explainability of Protein Language Models for Sequence Design
Transformer-based language models excel in a variety of protein-science tasks that range from structure prediction to the design of functional enzymes. However, these models operate as black boxes, and their underlying working principles remain unclear. Here, we survey emerging applications of explainable artificial intelligence (XAI) to protein language models (pLMs) and describe their potential in protein research. We break down the workflow of a generative decoder-only Transformer into four …

Category-based Galaxy Image Generation via Diffusion Models
Xingzhong Fan, Hongming Tang, Yue Zeng, M. B. N. Kouwenhoven, Guangquan Zeng
https://arxiv.org/abs/2506.16255

Category-based Galaxy Image Generation via Diffusion Models
Conventional galaxy generation methods rely on semi-analytical models and hydrodynamic simulations, which are highly dependent on physical assumptions and parameter tuning. In contrast, data-driven generative models do not have explicit physical parameters pre-determined, and instead learn them efficiently from observational data, making them alternative solutions to galaxy generation. Among these, diffusion models outperform Variational Autoencoders (VAEs) and Generative Adversarial Networks (…

Exact Conditional Score-Guided Generative Modeling for Amortized Inference in Uncertainty Quantification
Zezhong Zhang, Caroline Tatsuoka, Dongbin Xiu, Guannan Zhang
https://arxiv.org/abs/2506.18227

Exact Conditional Score-Guided Generative Modeling for Amortized Inference in Uncertainty Quantification
We propose an efficient framework for amortized conditional inference by leveraging exact conditional score-guided diffusion models to train a non-reversible neural network as a conditional generative model. Traditional normalizing flow methods require reversible architectures, which can limit their expressiveness and efficiency. Although diffusion models offer greater flexibility, they often suffer from high computational costs during inference. To combine the strengths of both approaches, we …

From Model Design to Organizational Design: Complexity Redistribution and Trade-Offs in Generative AI
Sharique Hasan, Alexander Oettl, Sampsa Samila
https://arxiv.org/abs/2506.22440

From Model Design to Organizational Design: Complexity Redistribution and Trade-Offs in Generative AI
This paper introduces the Generality-Accuracy-Simplicity (GAS) framework to analyze how large language models (LLMs) are reshaping organizations and competitive strategy. We argue that viewing AI as a simple reduction in input costs overlooks two critical dynamics: (a) the inherent trade-offs among generality, accuracy, and simplicity, and (b) the redistribution of complexity across stakeholders. While LLMs appear to defy the traditional trade-off by offering high generality and accuracy throug…

MemAscend: System Memory Optimization for SSD-Offloaded LLM Fine-Tuning
Yong-Cheng Liaw, Shuo-Han Chen
https://arxiv.org/abs/2505.23254 https://

MemAscend: System Memory Optimization for SSD-Offloaded LLM Fine-Tuning
Owing to the huge success of generative artificial intelligence (AI), large language models (LLMs) have emerged as a core subclass, underpinning applications such as question answering, text generation, and code completion. While fine-tuning these models on domain-specific data can yield significant performance gains, it also poses daunting computational challenges, especially for researchers and small organizations with limited hardware resources. Although SSD offloading (i.e., ZeRO-Infinity) …

CodeGuard: A Generalized and Stealthy Backdoor Watermarking for Generative Code Models
Haoxuan Li, Jiale Zhang, Xiaobing Sun, Xiapu Luo
https://arxiv.org/abs/2506.20926

CodeGuard: A Generalized and Stealthy Backdoor Watermarking for Generative Code Models
Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating effective digital copyright protection to prevent unauthorized leaks and misuse. Backdoor watermarking, by embedding hidden identifiers, simplifies copyright verification by breaking the model's black-box nature. Current backdoor watermarking techniques face two mai…

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
Matyas Bohacek, Thomas Fel, Maneesh Agrawala, Ekdeep Singh Lubana
https://arxiv.org/abs/2506.19708

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
Despite their impressive performance, generative image models trained on large-scale datasets frequently fail to produce images with seemingly simple concepts -- e.g., human hands or objects appearing in groups of four -- that are reasonably expected to appear in the training data. These failure modes have largely been documented anecdotally, leaving open the question of whether they reflect idiosyncratic anomalies or more structural limitations of these models. To address this, we introduce a …

Diffusion Model-based Data Augmentation Method for Fetal Head Ultrasound Segmentation
Fangyijie Wang, Kevin Whelan, F\'elix Balado, Gu\'enol\'e Silvestre, Kathleen M. Curran
https://arxiv.org/abs/2506.23664

Diffusion Model-based Data Augmentation Method for Fetal Head Ultrasound Segmentation
Medical image data is less accessible than in other domains due to privacy and regulatory constraints. In addition, labeling requires costly, time-intensive manual image annotation by clinical experts. To overcome these challenges, synthetic medical data generation offers a promising solution. Generative AI (GenAI), employing generative deep learning models, has proven effective at producing realistic synthetic images. This study proposes a novel mask-guided GenAI approach using diffusion model…

Analyzing Security and Privacy Challenges in Generative AI Usage Guidelines for Higher Education
Bei Yi Ng, Jiarui Li, Xinyuan Tong, Kevin Ye, Gauthami Yenne, Varun Chandrasekaran, Jingjie Li
https://arxiv.org/abs/2506.20463

Analyzing Security and Privacy Challenges in Generative AI Usage Guidelines for Higher Education
Educators and learners worldwide are embracing the rise of Generative Artificial Intelligence (GenAI) as it reshapes higher education. However, GenAI also raises significant privacy and security concerns, as models and privacy-sensitive user data, such as student records, may be misused by service providers. Unfortunately, end-users often have little awareness of or control over how these models operate. To address these concerns, universities are developing institutional policies to guide GenA…

CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design
Najmeh Forouzandehmehr, Reza Yousefi Maragheh, Sriram Kollipara, Kai Zhao, Topojoy Biswas, Evren Korpeoglu, Kannan Achan
https://arxiv.org/abs/2506.21934

CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design
Automated content-aware layout generation -- the task of arranging visual elements such as text, logos, and underlays on a background canvas -- remains a fundamental yet under-explored problem in intelligent design systems. While recent advances in deep generative models and large language models (LLMs) have shown promise in structured content generation, most existing approaches lack grounding in contextual design exemplars and fall short in handling semantic alignment and visual coherence. In…

The Age of Sensorial Zero Trust: Why We Can No Longer Trust Our Senses
Fabio Correa Xavier
https://arxiv.org/abs/2507.00907 https://a…

The Age of Sensorial Zero Trust: Why We Can No Longer Trust Our Senses
In a world where deepfakes and cloned voices are emerging as sophisticated attack vectors, organizations require a new security mindset: Sensorial Zero Trust [9]. This article presents a scientific analysis of the need to systematically doubt information perceived through the senses, establishing rigorous verification protocols to mitigate the risks of fraud based on generative artificial intelligence. Key concepts, such as Out-of-Band verification, Vision-Language Models (VLMs) as forensic col…

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
Yejing Wang, Shengyu Zhou, Jinyu Lu, Qidong Liu, Xinhang Li, Wenlin Zhang, Feng Li, Pengjie Wang, Jian Xu, Bo Zheng, Xiangyu Zhao
https://arxiv.org/abs/2506.16114

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexpl…

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
Louis Bradshaw, Honglu Fan, Alexander Spangher, Stella Biderman, Simon Colton
https://arxiv.org/abs/2506.23869

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
We study the capabilities of generative autoregressive transformer models trained on large amounts of symbolic solo-piano transcriptions. After first pretraining on approximately 60,000 hours of music, we use a comparatively smaller, high-quality subset, to finetune models to produce musical continuations, perform symbolic classification tasks, and produce general-purpose contrastive MIDI embeddings by adapting the SimCLR framework to symbolic music. When evaluating piano continuation coherence…

DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
Sanberk Serbest, Tijana Stojkovic, Milos Cernak, Andrew Harper
https://arxiv.org/abs/2505.23515

DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distribution, whereas generative models aim to learn the full distribution. This behavior of predictive models may lead to over-suppression, i.e. the removal of speech content. In the literature, it was shown that combining a predictive model with a generative one within the stochastic regeneration framework can reduce the …

Federated Breast Cancer Detection Enhanced by Synthetic Ultrasound Image Augmentation
Hongyi Pan, Ziliang Hong, Gorkem Durak, Ziyue Xu, Ulas Bagci
https://arxiv.org/abs/2506.23334

Federated Breast Cancer Detection Enhanced by Synthetic Ultrasound Image Augmentation
Federated learning (FL) has emerged as a promising paradigm for collaboratively training deep learning models across institutions without exchanging sensitive medical data. However, its effectiveness is often hindered by limited data availability and non-independent, identically distributed data across participating clients, which can degrade model performance and generalization. To address these challenges, we propose a generative AI based data augmentation framework that integrates synthetic …

Exposing the Impact of GenAI for Cybercrime: An Investigation into the Dark Side
Truong (Jack), Luu, Binny M. Samuel
https://arxiv.org/abs/2505.23733 http…

Exposing the Impact of GenAI for Cybercrime: An Investigation into the Dark Side
In recent years, the rapid advancement and democratization of generative AI models have sparked significant debate over safety, ethical risks, and dual-use concerns, particularly in the context of cybersecurity. While anecdotally known, this paper provides empirical evidence regarding generative AI's association with malicious internet-related activities and cybercrime by examining the phenomenon through psychological frameworks of technological amplification and affordance theory. Using a quas…

Multi-Objective Recommendation in the Era of Generative AI: A Survey of Recent Progress and Future Prospects
Zihan Hong, Yushi Wu, Zhiting Zhao, Shanshan Feng, Jianghong Ma, Jiao Liu, Tianjun Wei
https://arxiv.org/abs/2506.16893

Multi-Objective Recommendation in the Era of Generative AI: A Survey of Recent Progress and Future Prospects
With the recent progress in generative artificial intelligence (Generative AI), particularly in the development of large language models, recommendation systems are evolving to become more versatile. Unlike traditional techniques, generative AI not only learns patterns and representations from complex data but also enables content generation, data synthesis, and personalized experiences. This generative capability plays a crucial role in the field of recommendation systems, helping to address t…

Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models
Aloni Cohen
https://arxiv.org/abs/2506.19881 https://

Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models
Are there any conditions under which a generative model's outputs are guaranteed not to infringe the copyrights of its training data? This is the question of "provable copyright protection" first posed by Vyas, Kakade, and Barak (ICML 2023). They define near access-freeness (NAF) and propose it as sufficient for protection. This paper revisits the question and establishes new foundations for provable copyright protection -- foundations that are firmer both technically and legally. First, we sho…

GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models
Qifei Cui, Xinyu Lu
https://arxiv.org/abs/2506.21245 https://

GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models
This work introduces a novel framework for brain tumor segmentation leveraging pre-trained GANs and Unet architectures. By combining a global anomaly detection module with a refined mask generation network, the proposed model accurately identifies tumor-sensitive regions and iteratively enhances segmentation precision using adversarial loss constraints. Multi-modal MRI data and synthetic image augmentation are employed to improve robustness and address the challenge of limited annotated dataset…

Large-Scale Training Data Attribution for Music Generative Models via Unlearning
Woosung Choi, Junghyun Koo, Kin Wai Cheuk, Joan Serr\`a, Marco A. Mart\'inez-Ram\'irez, Yukara Ikemiya, Naoki Murata, Yuhta Takida, Wei-Hsiang Liao, Yuki Mitsufuji
https://arxiv.org/abs/2506.18312

Large-Scale Training Data Attribution for Music Generative Models via Unlearning
This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed to the generation of a particular output from a specific model. This is crucial in the context of AI-generated music, where proper recognition and credit for original artists are generally overlooked. By enabling white-box attribution, our work supports a fairer system for acknowledg…

Advanced Applications of Generative AI in Actuarial Science: Case Studies Beyond ChatGPT
Simon Hatzesberger, Iris Nonneman
https://arxiv.org/abs/2506.18942

Advanced Applications of Generative AI in Actuarial Science: Case Studies Beyond ChatGPT
This article demonstrates the transformative impact of Generative AI (GenAI) on actuarial science, illustrated by four implemented case studies. It begins with a historical overview of AI, tracing its evolution from early neural networks to modern GenAI technologies. The first case study shows how Large Language Models (LLMs) improve claims cost prediction by deriving significant features from unstructured textual data, significantly reducing prediction errors in the underlying machine learning…

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models
Julien Guinot, Elio Quinton, Gy\"orgy Fazekas
https://arxiv.org/abs/2506.17886

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models
Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems controllable and interactive for users. In text-music retrieval, the ambiguity of freeform language creates a many-to-many mapping, often resulting in inflexible or unsatisfying results. We introduce Generative Diffusion Retriever (GDR), a novel framework that l…

StableCodec: Taming One-Step Diffusion for Extreme Image Compression
Tianyu Zhang, Xin Luo, Li Li, Dong Liu
https://arxiv.org/abs/2506.21977 https://

StableCodec: Taming One-Step Diffusion for Extreme Image Compression
Diffusion-based image compression has shown remarkable potential for achieving ultra-low bitrate coding (less than 0.05 bits per pixel) with high realism, by leveraging the generative priors of large pre-trained text-to-image diffusion models. However, current approaches require a large number of denoising steps at the decoder to generate realistic results under extreme bitrate constraints, limiting their application in real-time compression scenarios. Additionally, these methods often sacrific…

ZeroSep: Separate Anything in Audio with Zero Training
Chao Huang, Yuesheng Ma, Junxuan Huang, Susan Liang, Yunlong Tang, Jing Bi, Wenqiang Liu, Nima Mesgarani, Chenliang Xu
https://arxiv.org/abs/2505.23625

ZeroSep: Separate Anything in Audio with Zero Training
Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data and struggle to generalize to the immense variability and open-set nature of real-world acoustic scenes. Inspired by the success of generative foundation models, we investigate whether pre-trained text-guided audio diffusion models c…