Tootfinder

Adobe launches AI Foundry, a new program to help enterprise customers create bespoke, commercially safe, Firefly-based generative AI models trained on their IP (Webb Wright/ZDNET)
https://www.zdnet.com/article/adobe-mightve-just-solved-one-o…

Adobe might've just solved one of generative AI's biggest legal risks
The company's new AI Foundry aims to help businesses build bespoke AI models with their own IP.

MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design
S. Rodionov, A. Burguete-Lopez, M. Makarenko, Q. Wang, F. Getman, A. Fratalocchi
https://arxiv.org/abs/2511.18980 https://arxiv.org/pdf/2511.18980 https://arxiv.org/html/2511.18980
arXiv:2511.18980v1 Announce Type: new
Abstract: Foundation models (FM) are transforming artificial intelligence by enabling generalizable, data-efficient solutions across different domains for a broad range of applications. However, the lack of large and diverse datasets limits the development of FM in nanophotonics. This work presents MOCLIP (Metasurface Optics Contrastive Learning Pretrained), a nanophotonic foundation model that integrates metasurface geometry and spectra within a shared latent space. MOCLIP employs contrastive learning to align geometry and spectral representations using an experimentally acquired dataset with a sample density comparable to ImageNet-1K. The study demonstrates MOCLIP inverse design capabilities for high-throughput zero-shot prediction at a rate of 0.2 million samples per second, enabling the design of a full 4-inch wafer populated with high-density metasurfaces in minutes. It also shows generative latent-space optimization reaching 97 percent accuracy. Finally, we introduce an optical information storage concept that uses MOCLIP to achieve a density of 0.1 Gbit per square millimeter at the resolution limit, exceeding commercial optical media by a factor of six. These results position MOCLIP as a scalable and versatile platform for next-generation photonic design and data-driven applications.
toXiv_bot_toot

Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance
Jincheng Zhong, Boyuan Jiang, Xin Tao, Pengfei Wan, Kun Gai, Mingsheng Long
https://arxiv.org/abs/2510.12497

Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance
Existing denoising generative models rely on solving discretized reverse-time SDEs or ODEs. In this paper, we identify a long-overlooked yet pervasive issue in this family of models: a misalignment between the pre-defined noise level and the actual noise level encoded in intermediate states during sampling. We refer to this misalignment as noise shift. Through empirical analysis, we demonstrate that noise shift is widespread in modern diffusion models and exhibits a systematic bias, leading to …

Inspections by Taiwan's National Security Bureau (NSB) of five Chinese generative AI apps -- Deepseek, Doubao (豆包), Yiyan (文心一言), Tongyi (通義千問), and Yuanbao (騰訊元寶) -- found violations of users' communication security across several indicators.
https://focustaiwan.tw/cross-strait/2025…

Taiwan warns of biases, data breach in Deepseek, other Chinese AI - Focus Taiwan
The National Security Bureau (NSB) has urged Taiwanese people to be on alert when using Chinese generative artificial intelligence (AI) language models due to potential security breaches and the spread of "disinformation" following recent inspections of five such apps.

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
Jiachen Lei, Keli Liu, Julius Berner, Haiming Yu, Hongkai Zheng, Jiahong Wu, Xiangxiang Chu
https://arxiv.org/abs/2510.12586

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficiency gap. In this paper, we introduce a novel two-stage training framework that closes this gap for pixel-space diffusion and consistency models. In the first stage, we pre-train encoders to capture meaningful semantics from clean images while aligning them with points along the same deterministic sampling trajectory, …

NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models
Fang Yuan, Junjie Zeng, Yue Hu, Zhengqiu Zhu, Quanjun Yin, Yuxiang Xie
https://arxiv.org/abs/2510.09355

NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models
SOAR, a classic symbol-based cognitive architecture, has been fostering the development of general, human-like intelligent agents. Nevertheless, its practical adoption is hindered by the laborious manual rule coding. Emerging Large Language Models (LLMs) present the immense potential for efficient rules generation. However, there is a critical gap that current research predominantly focuses on conceptual frameworks and lacks robust experimental validation. To bridge this gap, we propose \textit…

OneRec-Think: In-Text Reasoning for Generative Recommendation
Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, Pengfei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zixing Zhang, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

OneRec-Think: In-Text Reasoning for Generative Recommendation
The powerful generative capacity of Large Language Models (LLMs) has instigated a paradigm shift in recommendation. However, existing generative models (e.g., OneRec) operate as implicit predictors, critically lacking the capacity for explicit and controllable reasoning-a key advantage of LLMs. To bridge this gap, we propose OneRec-Think, a unified framework that seamlessly integrates dialogue, reasoning, and personalized recommendation. OneRec-Think incorporates: (1) Itemic Alignment: cross-mo…

Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models
David Layden, Ryan Sweke, Vojt\v{e}ch Havl\'i\v{c}ek, Anirban Chowdhury, Kirill Neklyudov
https://arxiv.org/abs/2510.08462

Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models
Flow models are a cornerstone of modern machine learning. They are generative models that progressively transform probability distributions according to learned dynamics. Specifically, they learn a continuous-time Markov process that efficiently maps samples from a simple source distribution into samples from a complex target distribution. We show that these models are naturally related to the Schrödinger equation, for an unusual Hamiltonian on continuous variables. Moreover, we prove that the…

Adapting Noise to Data: Generative Flows from 1D Processes
Jannis Chemseddine, Gregor Kornhardt, Richard Duong, Gabriele Steidl
https://arxiv.org/abs/2510.12636 https://

Adapting Noise to Data: Generative Flows from 1D Processes
We introduce a general framework for constructing generative models using one-dimensional noising processes. Beyond diffusion processes, we outline examples that demonstrate the flexibility of our approach. Motivated by this, we propose a novel framework in which the 1D processes themselves are learnable, achieved by parameterizing the noise distribution through quantile functions that adapt to the data. Our construction integrates seamlessly with standard objectives, including Flow Matching an…

Generative Latent Video Compression
Zongyu Guo, Zhaoyang Jia, Jiahao Li, Xiaoyi Zhang, Bin Li, Yan Lu
https://arxiv.org/abs/2510.09987 https://arxiv.org/pd…

Generative Latent Video Compression
Perceptual optimization is widely recognized as essential for neural compression, yet balancing the rate-distortion-perception tradeoff remains challenging. This difficulty is especially pronounced in video compression, where frame-wise quality fluctuations often cause perceptually optimized neural video codecs to suffer from flickering artifacts. In this paper, inspired by the success of latent generative models, we present Generative Latent Video Compression (GLVC), an effective framework for…

MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation
Akira Takahashi, Shusuke Takahashi, Yuki Mitsufuji
https://arxiv.org/abs/2510.09065

MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation
We introduce MMAudioSep, a generative model for video/text-queried sound separation that is founded on a pretrained video-to-audio model. By leveraging knowledge about the relationship between video/text and audio learned through a pretrained audio generative model, we can train the model more efficiently, i.e., the model does not need to be trained from scratch. We evaluate the performance of MMAudioSep by comparing it to existing separation models, including models based on both deterministic…

Generative AI and the Transformation of Software Development Practices
Vivek Acharya
https://arxiv.org/abs/2510.10819 https://arxiv.org/pdf/2510.10819

Generative AI and the Transformation of Software Development Practices
Generative AI is reshaping how software is designed, written, and maintained. Advances in large language models (LLMs) are enabling new development styles - from chat-oriented programming and 'vibe coding' to agentic programming - that can accelerate productivity and broaden access. This paper examines how AI-assisted techniques are changing software engineering practice, and the related issues of trust, accountability, and shifting skills. We survey iterative chat-based development, multi-agen…

Evolutionary Computation as Natural Generative AI
Yaxin Shi, Abhishek Gupta, Ying Wu, Melvin Wong, Ivor Tsang, Thiago Rios, Stefan Menzel, Bernhard Sendhoff, Yaqing Hou, Yew-Soon Ong
https://arxiv.org/abs/2510.08590

Evolutionary Computation as Natural Generative AI
Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning based on local gradient signals. This often results in artifacts that are more derivative than genuinely generative. In contrast, Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity, expanding generative capabilities by exploring uncharted solution spaces beyond the limits …

Failure Prediction at Runtime for Generative Robot Policies
Ralf R\"omer, Adrian Kobras, Luca Worbis, Angela P. Schoellig
https://arxiv.org/abs/2510.09459 https://

Failure Prediction at Runtime for Generative Robot Policies
Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. However, distribution shifts from unseen environments or compounding action errors can still cause unpredictable and unsafe behavior, leading to task failure. Early failure prediction during runtime is therefore essential for deploying robots in human-centered and safety-critical environments. We propose FIPER, a general framework for Failure Prediction…

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
Danial Hosseintabar, Fan Chen, Giannis Daras, Antonio Torralba, Constantinos Daskalakis
https://arxiv.org/abs/2510.12691

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains challenging. In this work, we propose a new method for training diffusion models with Expectation-Maximization (EM) from corrupted data. Our proposed method, DiffEM, utilizes conditional diffusion models to reconstruct clean data from observations in the E-step, and then uses the reconstructed data to refine the cond…

The Rise of the Knowledge Sculptor: A New Archetype for Knowledge Work in the Age of Generative AI
Cathal Doyle
https://arxiv.org/abs/2510.07829 https://ar…

The Rise of the Knowledge Sculptor: A New Archetype for Knowledge Work in the Age of Generative AI
In the Generative Age, the nature of knowledge work is transforming. Traditional models that emphasise the organisation and retrieval of pre-existing information are increasingly inadequate in the face of generative AI (GenAI) systems capable of autonomous content creation. This paper introduces the Knowledge Sculptor (KS), a new professional archetype for Human-GenAI collaboration that transforms raw AI output into trustworthy, actionable knowledge. Grounded in a socio-technical perspective, t…

Humain partners with Adobe and Qualcomm to develop AI tools for Arabic content, using Adobe's Firefly Foundry to build AI models and Qualcomm chips to run them (Stephen Nellis/Reuters)
https://www.reuters.com/world/middle-east/

MCMC: Bridging Rendering, Optimization and Generative AI
Gurprit Singh, Wenzel Jakob
https://arxiv.org/abs/2510.09078 https://arxiv.org/pdf/2510.09078

MCMC: Bridging Rendering, Optimization and Generative AI
Generative artificial intelligence (AI) has made unprecedented advances in vision language models over the past two years. During the generative process, new samples (images) are generated from an unknown high-dimensional distribution. Markov Chain Monte Carlo (MCMC) methods are particularly effective in drawing samples from such complex, high-dimensional distributions. This makes MCMC methods an integral component for models like EBMs, ensuring accurate sample generation. Gradient-based opti…

Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix
Etienne Levecque (LIST3N), Aur\'elien Noirault (CRIStAL), Tom\'a\v{s} Pevn\'y (CTU), Jan Butora (CRIStAL), Patrick Bas (CRIStAL), R\'emi Cogranne (LIST3N)
https://arxiv.org/abs/2510.12414

Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix
Steganographic schemes dedicated to generated images modify the seed vector in the latent space to embed a message, whereas most steganalysis methods attempt to detect the embedding in the image space. This paper proposes to perform steganalysis in the latent space by modeling the statistical distribution of the norm of the latent vector. Specifically, we analyze the practical security of a scheme proposed by Hu et. al. for latent diffusion models, which is both robust and practically undetecta…

Generative Diffusion Model DiffCrysGen Discovers Rare Earth-Free Magnetic Materials
Sourav Mal, Nehad Ahmed, Subhankar Mishra, Prasenjit Sen
https://arxiv.org/abs/2510.12329 htt…

Generative Diffusion Model DiffCrysGen Discovers Rare Earth-Free Magnetic Materials
Efficient exploration of the vast chemical space is a fundamental challenge in materials discovery, particularly for designing functional inorganic crystalline materials with targeted properties. Diffusion-based generative models have emerged as a powerful route, but most existing approaches require domain-specific constraints and separate diffusion processes for atom types, atomic positions, and lattice parameters, adding complexity and limiting efficiency. Here, we present DiffCrysGen, a full…

Domain Knowledge Infused Generative Models for Drug Discovery Synthetic Data
Bing Hu, Jong-Hoon Park, Helen Chen, Young-Rae Cho, Anita Layton
https://arxiv.org/abs/2510.09837 ht…

Domain Knowledge Infused Generative Models for Drug Discovery Synthetic Data
The role of Artificial Intelligence (AI) is growing in every stage of drug development. Nevertheless, a major challenge in drug discovery AI remains: Drug pharmacokinetic (PK) and Drug-Target Interaction (DTI) datasets collected in different studies often exhibit limited overlap, creating data overlap sparsity. Thus, data curation becomes difficult, negatively impacting downstream research investigations in high-throughput screening, polypharmacy, and drug combination. We propose xImagand-DKI, …

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Tobias Preintner, Weixuan Yuan, Adrian K\"onig, Thomas B\"ack, Elena Raponi, Niki van Stein
https://arxiv.org/abs/2510.11631

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Combining large language models with evolutionary computation algorithms represents a promising research direction leveraging the remarkable generative and in-context learning capabilities of LLMs with the strengths of evolutionary algorithms. In this work, we present EvoCAD, a method for generating computer-aided design (CAD) objects through their symbolic representations using vision language models and evolutionary optimization. Our method samples multiple CAD objects, which are then optimiz…

StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
Chenyu Zhou, Tianyi Xu, Jianghao Lin, Dongdong Ge
https://arxiv.org/abs/2509.22558

StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
Large Language Models (LLMs) have shown promising capabilities for solving Operations Research (OR) problems. While reinforcement learning serves as a powerful paradigm for LLM training on OR problems, existing works generally face two key limitations. First, outcome reward suffers from the credit assignment problem, where correct final answers can reinforce flawed reasoning. Second, conventional discriminative process supervision is myopic, failing to evaluate the interdependent steps of OR mo…

The Mechanical Yes-Man: Emancipatory AI Pedagogy in Higher Education
Linda Rocco
https://arxiv.org/abs/2510.10176 https://arxiv.org/pdf/2510.10176

The Mechanical Yes-Man: Emancipatory AI Pedagogy in Higher Education
The proliferation of Large Language Models in higher education presents a fundamental challenge to traditional pedagogical frameworks. Drawing on Jacques Rancière's theory of intellectual emancipation, this paper examines how generative AI risks becoming a "mechanical yes-man" that reinforces passivity rather than fostering intellectual autonomy. Generative AI's statistical logic and lack of causal reasoning, combined with frictionless information access, threatens to hollow out cognitive proc…

What Generative Search Engines Like and How to Optimize Web Content Cooperatively
Yujiang Wu, Shanshan Zhong, Yubin Kim, Chenyan Xiong
https://arxiv.org/abs/2510.11438 https://

What Generative Search Engines Like and How to Optimize Web Content Cooperatively
By employing large language models (LLMs) to retrieve documents and generate natural language responses, Generative Engines, such as Google AI overview and ChatGPT, provide significantly enhanced user experiences and have rapidly become the new form of search. Their rapid adoption also drives the needs of Generative Engine Optimization (GEO), as content providers are eager to gain more traction from them. In this paper, we introduce AutoGEO, a framework to automatically learn generative engine …

Offline Reinforcement Learning with Generative Trajectory Policies
Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen
https://arxiv.org/abs/2510.11499 https://

Offline Reinforcement Learning with Generative Trajectory Policies
Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while fast, single-step models like consistency policies often suffer from degraded performance. In this paper, we demonstrate that it is possible to bridge this gap. The key to moving beyond the limitati…

DeepMind: video models like Veo 3 could become general purpose foundation models for vision, like LLMs for text, using zero-shot "chain-of-frames" reasoning (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Sep/27/v…

Video models are zero-shot learners and reasoners
Fascinating new paper from Google DeepMind which makes a very convincing case that their Veo 3 model - and generative video models in general - serve a similar role in …

🔮 The Future: Z1 Scale-Up Coming next: Z1 chips with 250K interconnected Pits per chip. Powers energy-based models 10,000x more efficient than #GPUs for generative tasks. Check the new paper on Denoising Thermodynamic #Models!
📺 Watch the full video:

Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamics
Juan Viguera Diez, Mathias Schreiner, Simon Olsson
https://arxiv.org/abs/2510.07589 …

Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamics
Understanding molecular structure, dynamics, and reactivity requires bridging processes that occur across widely separated time scales. Conventional molecular dynamics simulations provide atomistic resolution, but their femtosecond time steps limit access to the slow conformational changes and relaxation processes that govern chemical function. Here, we introduce a deep generative modeling framework that accelerates sampling of molecular dynamics by four orders of magnitude while retaining phys…

FLAME: A Serving System Optimized for Large-Scale Generative Recommendation with Efficiency
Xianwen Guo, Bin Huang, Xiaomeng Wu, Guanlin Wu, Fangjian Li, Shijia Wang, Qiang Xiao, Chuanjiang Luo, Yong Li
https://arxiv.org/abs/2509.22681

FLAME: A Serving System Optimized for Large-Scale Generative Recommendation with Efficiency
Generative recommendation (GR) models possess greater scaling power compared to traditional deep learning recommendation models (DLRMs), yet they also impose a tremendous increase in computational burden. Measured in FLOPs, a typical GR model's workload sits in $10^9 \sim 10^{11}$ range, roughly four orders of magnitude higher than traditional DLRMs. Delivering accurate results in a few tens of milliseconds while processing billions of such requests per day puts extreme demands on the performan…

On (generative) AI:
"So it's sort of like when we fed cows with cows and got mad cow disease."
https://framapiaf.org/@bbbhltz/115646412773089943

Physicochemically Informed Dual-Conditioned Generative Model of T-Cell Receptor Variable Regions for Cellular Therapy
Jiahao Ma, Hongzong Li, Ye-Fan Hu, Jian-Dong Huang
https://arxiv.org/abs/2510.05747

Physicochemically Informed Dual-Conditioned Generative Model of T-Cell Receptor Variable Regions for Cellular Therapy
Physicochemically informed biological sequence generation has the potential to accelerate computer-aided cellular therapy, yet current models fail to \emph{jointly} ensure novelty, diversity, and biophysical plausibility when designing variable regions of T-cell receptors (TCRs). We present \textbf{PhysicoGPTCR}, a large generative protein Transformer that is \emph{dual-conditioned} on peptide and HLA context and trained to autoregressively synthesise TCR sequences while embedding residue-level…

I loved @jasonclark.bsky.social 's #FF2025 'problem statement':
'We were given access to a weirdly confident intern that can’t explain how they got their answers.
It is a seamless interface that breaks search interaction retrieval patterns.'

{ "jason": "clark" } (@jasonclark.bsky.social)
Slides and code from my #ff2025 talk, "Reasoning with Small Language Models (SLM) for Trustworthy Generative AI (GenAI)." Slides: https://docs.google.com/presentation/d/1NHCuyuPd9KK3QUo8izeta2CMIk-rmcy1/edit?usp=drive_link&ouid=103883366387427181221&rtpof=true&sd=true Code: https://github.com/jasonclark/agentic-search-react

Universality and kernel-adaptive training for classically trained, quantum-deployed generative models
Andrii Kurkin, Kevin Shen, Susanne Pielawa, Hao Wang, Vedran Dunjko
https://arxiv.org/abs/2510.08476

Universality and kernel-adaptive training for classically trained, quantum-deployed generative models
The instantaneous quantum polynomial (IQP) quantum circuit Born machine (QCBM) has been proposed as a promising quantum generative model over bitstrings. Recent works have shown that the training of IQP-QCBM is classically tractable w.r.t. the so-called Gaussian kernel maximum mean discrepancy (MMD) loss function, while maintaining the potential of a quantum advantage for sampling itself. Nonetheless, the model has a number of aspects where improvements would be important for more general utili…

Neural Jump ODEs as Generative Models
Robert A. Crowell, Florian Krach, Josef Teichmann
https://arxiv.org/abs/2510.02757 https://arxiv.org/pdf/2510.02757…

Neural Jump ODEs as Generative Models
In this work, we explore how Neural Jump ODEs (NJODEs) can be used as generative models for Itô processes. Given (discrete observations of) samples of a fixed underlying Itô process, the NJODE framework can be used to approximate the drift and diffusion coefficients of the process. Under standard regularity assumptions on the Itô processes, we prove that, in the limit, we recover the true parameters with our approximation. Hence, using these learned coefficients to sample from the correspond…

Exploring Human-AI Collaboration Using Mental Models of Early Adopters of Multi-Agent Generative AI Tools
Suchismita Naik, Austin L. Toombs, Amanda Snellinger, Scott Saponas, Amanda K. Hall
https://arxiv.org/abs/2510.06224

Exploring Human-AI Collaboration Using Mental Models of Early Adopters of Multi-Agent Generative AI Tools
With recent advancements in multi-agent generative AI (Gen AI), technology organizations like Microsoft are adopting these complex tools, redefining AI agents as active collaborators in complex workflows rather than as passive tools. In this study, we investigated how early adopters and developers conceptualize multi-agent Gen AI tools, focusing on how they understand human-AI collaboration mechanisms, general collaboration dynamics, and transparency in the context of AI tools. We conducted sem…

Memory-Augmented Generative AI for Real-time Wireless Prediction in Dynamic Industrial Environments
Rahul Gulia, Amlan Ganguly, Michael E. Kuhl, Ehsan Rashedi, Clark Hochgraf
https://arxiv.org/abs/2510.06884

Memory-Augmented Generative AI for Real-time Wireless Prediction in Dynamic Industrial Environments
Accurate and real-time prediction of wireless channel conditions, particularly the Signal-to-Interference-plus-Noise Ratio (SINR), is a foundational requirement for enabling Ultra-Reliable Low-Latency Communication (URLLC) in highly dynamic Industry 4.0 environments. Traditional physics-based or statistical models fail to cope with the spatio-temporal complexities introduced by mobile obstacles and transient interference inherent to smart warehouses. To address this, we introduce Evo-WISVA (Evo…

EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
Maybritt Schillinger, Maxim Samarin, Xinwei Shen, Reto Knutti, Nicolai Meinshausen
https://arxiv.org/abs/2509.26258

EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
The practical use of future climate projections from global circulation models (GCMs) is often limited by their coarse spatial resolution, requiring downscaling to generate high-resolution data. Regional climate models (RCMs) provide this refinement, but are computationally expensive. To address this issue, machine learning models can learn the downscaling function, mapping coarse GCM outputs to high-resolution fields. Among these, generative approaches aim to capture the full conditional distr…

Who are you, ChatGPT? Personality and Demographic Style in LLM-Generated Content
Dana Sotto Porat, Ella Rabinovich
https://arxiv.org/abs/2510.11434 https://

Who are you, ChatGPT? Personality and Demographic Style in LLM-Generated Content
Generative large language models (LLMs) have become central to everyday life, producing human-like text across diverse domains. A growing body of research investigates whether these models also exhibit personality- and demographic-like characteristics in their language. In this work, we introduce a novel, data-driven methodology for assessing LLM personality without relying on self-report questionnaires, applying instead automatic personality and gender classifiers to model replies on open-ende…

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Weiwei Sun, Keyi Kong, Xinyu Ma, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, Zhaochun Ren, Yiming Yang
https://arxiv.org/abs/2510.10419

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids), thereby enabling an end-to-end optimization and seamless integration with generative language models (LMs). Despite notable progress under supervised training, GR still struggles to generalize to zero-shot IR scenarios, which are prevalent in real-world applications. To tackle this challenge, we propose \textsc{ZeroGR}, a zero-shot generative retrieval framework th…

Improving Speech Emotion Recognition with Mutual Information Regularized Generative Model
Chung-Soo Ahn, Rajib Rana, Sunil Sivadas, Carlos Busso, Jagath C. Rajapakse
https://arxiv.org/abs/2510.10078

Improving Speech Emotion Recognition with Mutual Information Regularized Generative Model
Although speech emotion recognition (SER) research has been advanced, thanks to deep learning methods, it still suffers from obtaining inputs from large quality-labelled training data. Data augmentation methods have been attempted to mitigate this issue, generative models have shown success among them recently. We propose a data augmentation framework that is aided by cross-modal information transfer and mutual information regularization. Mutual information based metric can serve as an indicato…

Exposing Citation Vulnerabilities in Generative Engines
Riku Mochizuki, Shusuke Komatsu, Souta Noguchi, Kazuto Ataka
https://arxiv.org/abs/2510.06823 https://

Exposing Citation Vulnerabilities in Generative Engines
We analyze answers generated by generative engines (GEs) from the perspectives of citation publishers and the content-injection barrier, defined as the difficulty for attackers to manipulate answers to user prompts by placing malicious content on the web. GEs integrate two functions: web search and answer generation that cites web pages using large language models. Because anyone can publish information on the web, GEs are vulnerable to poisoning attacks. Existing studies of citation evaluation…

What Drives Compositional Generalization in Visual Generative Models?
Karim Farid, Rajat Sahay, Yumna Ali Alnaggar, Simon Schrodi, Volker Fischer, Cordelia Schmid, Thomas Brox
https://arxiv.org/abs/2510.03075

What Drives Compositional Generalization in Visual Generative Models?
Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechanisms that enable or inhibit it are fully understood. In this work, we conduct a systematic study of how various design choices influence compositional generalization in image and video generation in a positive or negative way. Through controlled experiments, we identify two key factors: (i) whether the training objective operates on a d…

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
Sangyun Lee, Brandon Amos, Giulia Fanti
https://arxiv.org/abs/2510.09596 https://

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
Today's generative models thrive with large amounts of supervised data and informative reward functions characterizing the quality of the generation. They work under the assumptions that the supervised data provides knowledge to pre-train the model, and the reward function provides dense information about how to further improve the generation quality and correctness. However, in the hardest instances of important problems, two problems arise: (1) the base generative model attains a near-zero re…

Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representation
Yu-Zhe Shi, Qiao Xu, Yanjia Li, Mingchen Liu, Huamin Qu, Lecheng Ruan, Qining Wang
https://arxiv.org/abs/2510.02679

Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representation
Advanced Planning and Scheduling (APS) systems have become indispensable for modern manufacturing operations, enabling optimized resource allocation and production efficiency in increasingly complex and dynamic environments. While algorithms for solving abstracted scheduling problems have been extensively investigated, the critical prerequisite of specifying manufacturing requirements into formal constraints remains manual and labor-intensive. Although recent advances of generative models, part…

SER-Diff: Synthetic Error Replay Diffusion for Incremental Brain Tumor Segmentation
Sashank Makanaboyina
https://arxiv.org/abs/2510.06283 https://arxiv.org…

SER-Diff: Synthetic Error Replay Diffusion for Incremental Brain Tumor Segmentation
Incremental brain tumor segmentation is critical for models that must adapt to evolving clinical datasets without retraining on all prior data. However, catastrophic forgetting, where models lose previously acquired knowledge, remains a major obstacle. Recent incremental learning frameworks with knowledge distillation partially mitigate forgetting but rely heavily on generative replay or auxiliary storage. Meanwhile, diffusion models have proven effective for refining tumor segmentations, but h…

(R)evolution of Programming: Vibe Coding as a Post-Coding Paradigm
Kevin Krings, Nino S. Bohn, Thomas Ludwig
https://arxiv.org/abs/2510.12364 https://arxiv…

(R)evolution of Programming: Vibe Coding as a Post-Coding Paradigm
Recent advancements in generative artificial intelligence (GenAI), particularly large language models, have introduced new possibilities for software development practices. In our paper we investigate the emerging Vibe Coding (VC) paradigm that emphasizes intuitive, affect-driven, and improvisational interactions between developers and AI systems. Building upon the discourse of End-User Development (EUD), we explore how VC diverges from conventional programming approaches such as those supporte…

ConQuER: Modular Architectures for Control and Bias Mitigation in IQP Quantum Generative Models
Xiaocheng Zou, Shijin Duan, Charles Fleming, Gaowen Liu, Ramana Rao Kompella, Shaolei Ren, Xiaolin Xu
https://arxiv.org/abs/2509.22551

ConQuER: Modular Architectures for Control and Bias Mitigation in IQP Quantum Generative Models
Quantum generative models based on instantaneous quantum polynomial (IQP) circuits show great promise in learning complex distributions while maintaining classical trainability. However, current implementations suffer from two key limitations: lack of controllability over generated outputs and severe generation bias towards certain expected patterns. We present a Controllable Quantum Generative Framework, ConQuER, which addresses both challenges through a modular circuit architecture. ConQuER e…

GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving
Ruida Wang, Jiarui Yao, Rui Pan, Shizhe Diao, Tong Zhang
https://arxiv.org/abs/2510.11769 https://

GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving
Solving math problems through verifiable languages such as Lean has significantly impacted both the mathematics and computer science communities. Current state-of-the-art models are often trained with expensive online Reinforcement Learning (RL) or expert iteration. However, these approaches rely on fixed problem sets, which causes inefficient training and limits the model to tackle complex problems. To overcome these limitations, we propose GAR: Generative Adversarial Reinforcement learning, a…

EigenScore: OOD Detection using Covariance in Diffusion Models
Shirin Shoushtari, Yi Wang, Xiao Shi, M. Salman Asif, Ulugbek S. Kamilov
https://arxiv.org/abs/2510.07206 https://…

EigenScore: OOD Detection using Covariance in Diffusion Models
Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems in safety-sensitive domains. Diffusion models have recently emerged as powerful generative models, capable of capturing complex data distributions through iterative denoising. Building on this progress, recent work has explored their potential for OOD detection. We propose EigenScore, a new OOD detection method that leverages the eigenvalue spectrum of the posterior covariance induced by a diffus…

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Stephen Ni-Hahn, Chao P\'eter Yang, Mingchen Ma, Cynthia Rudin, Simon Mak, Yue Jiang
https://arxiv.org/abs/2510.10249

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Artificial Intelligence (AI) for music generation is undergoing rapid developments, with recent symbolic models leveraging sophisticated deep learning and diffusion model algorithms. One drawback with existing models is that they lack structural cohesion, particularly on harmonic-melodic structure. Furthermore, such existing models are largely "black-box" in nature and are not musically interpretable. This paper addresses these limitations via a novel generative music framework that incorporate…

PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
Ruining He, Lukasz Heldt, Lichan Hong, Raghunandan Keshavan, Shifan Mao, Nikhil Mehta, Zhengyang Su, Alicia Tsai, Yueqi Wang, Shao-Chuan Wang, Xinyang Yi, Lexi Baugher, Baykal Cakici, Ed Chi, Cristos Goodrow, Ningren Han, He Ma, Romer Rosales, Abby Van Soest, Devansh Tandon, Su-Lin Wu, Weilong Yang, Yilin Zheng

PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
Large Language Models (LLMs) pose a new paradigm of modeling and computation for information tasks. Recommendation systems are a critical application domain poised to benefit significantly from the sequence modeling capabilities and world knowledge inherent in these large models. In this paper, we introduce PLUM, a framework designed to adapt pre-trained LLMs for industry-scale recommendation tasks. PLUM consists of item tokenization using Semantic IDs, continued pre-training (CPT) on domain-sp…

Benefits and Limitations of Using GenAI for Political Education and Municipal Elections
Raphael Fischer, Youssef Abdelrahim, Katharina Poitz
https://arxiv.org/abs/2510.11749 htt…

Benefits and Limitations of Using GenAI for Political Education and Municipal Elections
Generative artificial intelligence (GenAI) presents both challenges and opportunities across all areas of education. Facing the municipal elections in North Rhine-Westphalia, the Young AI Leaders in Dortmund asked themselves: Could GenAI be used to make political programs more accessible, in order to facilitate political education? To explore respective potentials and limitations, we therefore performed an experimental study that combines different GenAI approaches. Language models were used to…

Define latent spaces by example: optimisation over the outputs of generative models
Samuel Willis, Alexandru I. Stere, Dragos D. Margineantu, Henry T. Oldroyd, John A. Fozard, Carl Henrik Ek, Henry Moss, Erik Bodin
https://arxiv.org/abs/2509.23800

Define latent spaces by example: optimisation over the outputs of generative models
Modern generative AI models such as diffusion and flow matching can sample from rich data distributions, but many downstream tasks -- such as experimental design or creative content generation -- require a higher level of control than unconstrained sampling. The challenge is to efficiently identify outputs that are both probable under the model and satisfy task-specific constraints. We address this by introducing surrogate latent spaces: non-parametric, low-dimensional Euclidean embeddings that…

3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning
Chenyuan Chen, Haoran Ding, Ran Ding, Tianyu Liu, Zewen He, Anqing Duan, Dezhen Song, Xiaodan Liang, Yoshihiko Nakamura
https://arxiv.org/abs/2510.03011

3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning
Diffusion models, as a class of deep generative models, have recently emerged as powerful tools for robot skills by enabling stable training with reliable convergence. In this paper, we present an end-to-end framework for generating long, smooth trajectories that explicitly target high surface coverage across various industrial tasks, including polishing, robotic painting, and spray coating. The conventional methods are always fundamentally constrained by their predefined functional forms, whic…

STaR-Attack: A Spatio-Temporal and Narrative Reasoning Attack Framework for Unified Multimodal Understanding and Generation Models
Shaoxiong Guo, Tianyi Du, Lijun Li, Yuyao Wu, Jie Li, Jing Shao
https://arxiv.org/abs/2509.26473

STaR-Attack: A Spatio-Temporal and Narrative Reasoning Attack Framework for Unified Multimodal Understanding and Generation Models
Unified Multimodal understanding and generation Models (UMMs) have demonstrated remarkable capabilities in both understanding and generation tasks. However, we identify a vulnerability arising from the generation-understanding coupling in UMMs. The attackers can use the generative function to craft an information-rich adversarial image and then leverage the understanding function to absorb it in a single pass, which we call Cross-Modal Generative Injection (CMGI). Current attack methods on mali…

DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism
Chenyu Jiang, Zhenkun Cai, Ye Tian, Zhen Jia, Yida Wang, Chuan Wu
https://arxiv.org/abs/2510.10620

DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism
Context parallelism has emerged as a key technique to support long-context training, a growing trend in generative AI for modern large models. However, existing context parallel methods rely on static parallelization configurations that overlook the dynamic nature of training data, specifically, the variability in sequence lengths and token relationships (i.e., attention patterns) across samples. As a result, these methods often suffer from unnecessary communication overhead and imbalanced comp…

Weighted Stochastic Differential Equation to Implement Wasserstein-Fisher-Rao Gradient Flow
Herlock Rahimi
https://arxiv.org/abs/2512.17878 https://arxiv.org/pdf/2512.17878 https://arxiv.org/html/2512.17878
arXiv:2512.17878v1 Announce Type: new
Abstract: Score-based diffusion models currently constitute the state of the art in continuous generative modeling. These methods are typically formulated via overdamped or underdamped Ornstein--Uhlenbeck-type stochastic differential equations, in which sampling is driven by a combination of deterministic drift and Brownian diffusion, resulting in continuous particle trajectories in the ambient space. While such dynamics enjoy exponential convergence guarantees for strongly log-concave target distributions, it is well known that their mixing rates deteriorate exponentially in the presence of nonconvex or multimodal landscapes, such as double-well potentials. Since many practical generative modeling tasks involve highly non-log-concave target distributions, considerable recent effort has been devoted to developing sampling schemes that improve exploration beyond classical diffusion dynamics.
A promising line of work leverages tools from information geometry to augment diffusion-based samplers with controlled mass reweighting mechanisms. This perspective leads naturally to Wasserstein--Fisher--Rao (WFR) geometries, which couple transport in the sample space with vertical (reaction) dynamics on the space of probability measures. In this work, we formulate such reweighting mechanisms through the introduction of explicit correction terms and show how they can be implemented via weighted stochastic differential equations using the Feynman--Kac representation. Our study provides a preliminary but rigorous investigation of WFR-based sampling dynamics, and aims to clarify their geometric and operator-theoretic structure as a foundation for future theoretical and algorithmic developments.
toXiv_bot_toot

Fal, which hosts generative AI models for developers, raised a $140M Series D led by Sequoia, a source says at a $4.5B valuation, up from $1.5B in July (Paayal Zaveri/Bloomberg)
https://www.bloomberg.com/news/articles/2025…

SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation
Ayush Zenith, Arnold Zumbrun, Neel Raut, Jing Lin
https://arxiv.org/abs/2510.06596 https://

SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation
The performance of machine learning models depends heavily on training data. The scarcity of large-scale, well-annotated datasets poses significant challenges in creating robust models. To address this, synthetic data generated through simulations and generative models has emerged as a promising solution, enhancing dataset diversity and improving the performance, reliability, and resilience of models. However, evaluating the quality of this generated data requires an effective metric. This pape…

GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
Oussama Gabouj, Kamel Charaf, Ivan Zakazov, Nicolas Baldwin, Robert West
https://arxiv.org/abs/2510.01165

GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but its reliance on static databases constrains adaptability and can result in irrelevant demonstrations. In this work, we propose a Generative Retrieval-Aligned Demonstrator (GRAD), a dynamic demonstration-based approach where an LLM model is trained to generat…

Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Chen Gao, Zixin Zhao, Lv Shao, Tong Liu
https://arxiv.org/abs/2510.11317

Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Click-Through Rate (CTR) prediction, a cornerstone of modern recommender systems, has been dominated by discriminative models that react to past user behavior rather than proactively modeling user intent. Existing generative paradigms attempt to address this but suffer from critical limitations: Large Language Model (LLM) based methods create a semantic mismatch by forcing e-commerce signals into a linguistic space, while ID-based generation is constrained by item memorization and cold-start is…

GenIA-E2ETest: A Generative AI-Based Approach for End-to-End Test Automation
Elvis J\'unior, Alan Valejo, Jorge Valverde-Rebaza, V\^ania de Oliveira Neves
https://arxiv.org/abs/2510.01024

GenIA-E2ETest: A Generative AI-Based Approach for End-to-End Test Automation
Software testing is essential to ensure system quality, but it remains time-consuming and error-prone when performed manually. Although recent advances in Large Language Models (LLMs) have enabled automated test generation, most existing solutions focus on unit testing and do not address the challenges of end-to-end (E2E) testing, which validates complete application workflows from user input to final system response. This paper introduces GenIA-E2ETest, which leverages generative AI to generat…

HSBC signs a deal with Mistral to access Mistral's AI models and collaborate on developing new models for internal use, as big banks rush to adopt generative AI (Ortenca Aliaj/Financial Times)
https://www.ft.com/content/7b8e4ea8-ae17-4ada-9117-9f859589ce1d

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
Runqian Wang, Yilun Du
https://arxiv.org/abs/2510.02300 https://arxiv.org/pdf/2…

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based generative models and instead learns the equilibrium gradient of an implicit energy landscape. Through this approach, we can adopt an optimization-based sampling process at inference time, where samples are obtained by gradient descent on the learned landscape with adjustable s…

A Hybrid CAPTCHA Combining Generative AI with Keystroke Dynamics for Enhanced Bot Detection
Ayda Aghaei Nia
https://arxiv.org/abs/2510.02374 https://arxiv.…

A Hybrid CAPTCHA Combining Generative AI with Keystroke Dynamics for Enhanced Bot Detection
Completely Automated Public Turing tests to tell Computers and Humans Apart (CAPTCHAs) are a foundational component of web security, yet traditional implementations suffer from a trade-off between usability and resilience against AI-powered bots. This paper introduces a novel hybrid CAPTCHA system that synergizes the cognitive challenges posed by Large Language Models (LLMs) with the behavioral biometric analysis of keystroke dynamics. Our approach generates dynamic, unpredictable questions tha…

Beyond Linear Diffusions: Improved Representations for Rare Conditional Generative Modeling
Kulunu Dharmakeerthi, Yousef El-Laham, Henry H. Wong, Vamsi K. Potluru, Changhong He, Taosong He
https://arxiv.org/abs/2510.02499

Beyond Linear Diffusions: Improved Representations for Rare Conditional Generative Modeling
Diffusion models have emerged as powerful generative frameworks with widespread applications across machine learning and artificial intelligence systems. While current research has predominantly focused on linear diffusions, these approaches can face significant challenges when modeling a conditional distribution, $P(Y|X=x)$, when $P(X=x)$ is small. In these regions, few samples, if any, are available for training, thus modeling the corresponding conditional density may be difficult. Recog…

Can World Models Benefit VLMs for World Dynamics?
Kevin Zhang, Kuangzhi Ge, Xiaowei Chi, Renrui Zhang, Shaojun Shi, Zhen Dong, Sirui Han, Shanghang Zhang
https://arxiv.org/abs/2510.00855

Can World Models Benefit VLMs for World Dynamics?
Trained on internet-scale video data, generative world models are increasingly recognized as powerful world simulators that can generate consistent and plausible dynamics over structure, motion, and physics. This raises a natural question: with the advent of strong video foundational models, might they supplant conventional vision encoder paradigms for general-purpose multimodal understanding? While recent studies have begun to explore the potential of world models on common vision tasks, these…

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Qiya Yang, Xiaoxi Liang, Zeping Xiao, Yingjie Deng, Yalong Wang, Yongqi Liu, Han Li
https://arxiv.org/abs/2510.10127

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Reranking, as the final stage of recommender systems, demands real-time inference, accuracy, and diversity. It plays a crucial role in determining the final exposure, directly influencing user experience. Recently, generative reranking has gained increasing attention for its strong ability to model complex dependencies among items. However, most existing methods suffer from the "likelihood trap", where high-likelihood sequences are often perceived as low-quality by humans. These models tend to …

Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
Szymon {\L}ukasik, Natalia O\.zegalska-{\L}ukasik
https://arxiv.org/abs/2509.25286

Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
Political beliefs vary significantly across different countries, reflecting distinct historical, cultural, and institutional contexts. These ideologies, ranging from liberal democracies to rigid autocracies, influence human societies, as well as the digital systems that are constructed within those societies. The advent of generative artificial intelligence, particularly Large Language Models (LLMs), introduces new agents in the political space-agents trained on massive corpora that replicate a…

A Theoretical Analysis of Discrete Flow Matching Generative Models
Maojiang Su, Mingcheng Lu, Jerry Yao-Chieh Hu, Shang Wu, Zhao Song, Alex Reneau, Han Liu
https://arxiv.org/abs/2509.22623

A Theoretical Analysis of Discrete Flow Matching Generative Models
We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generative dynamics by training a neural network to approximate the transformative velocity field. Our analysis establishes a clear chain of guarantees by decomposing the final distribution estimation error. We first prove that the total variation distance between the generated and target distributions is c…

Scaling Language-Centric Omnimodal Representation Learning
Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong
https://arxiv.org/abs/2510.11693 https://…

Scaling Language-Centric Omnimodal Representation Learning
Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored. This work argues that a crucial advantage of MLLM-based approaches stems from implicit cross-modal alignment achieved during generative pretraining, where the language decoder learns to exploit multimodal signals within a shared representation space for generati…

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
Zhehao Dong, Xiaofeng Wang, Zheng Zhu, Yirui Wang, Yang Wang, Yukun Zhou, Boyuan Wang, Chaojun Ni, Runqi Ouyang, Wenkang Qin, Xinze Chen, Yun Ye, Guan Huang
https://arxiv.org/abs/2509.22407

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
Vision-language-action (VLA) models increasingly rely on diverse training data to achieve robust generalization. However, collecting large-scale real-world robot manipulation data across varied object appearances and environmental conditions remains prohibitively time-consuming and expensive. To overcome this bottleneck, we propose Embodied Manipulation Media Adaptation (EMMA), a VLA policy enhancement framework that integrates a generative data engine with an effective training pipeline. We in…

InfiniHuman: Infinite 3D Human Creation with Precise Control
Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll
https://arxiv.org/abs/2510.11650 https://

InfiniHuman: Infinite 3D Human Creation with Precise Control
Generating realistic and controllable 3D human avatars is a long-standing challenge, particularly when covering broad attribute ranges such as ethnicity, age, clothing styles, and detailed body shapes. Capturing and annotating large-scale human datasets for training generative models is prohibitively expensive and limited in scale and diversity. The central question we address in this paper is: Can existing foundation models be distilled to generate theoretically unbounded, richly annotated 3D …

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/5]:
- Look-Ahead Reasoning on Learning Platforms
Haiqing Zhu, Tijana Zrnic, Celestine Mendler-D\"unner
https://arxiv.org/abs/2511.14745 https://mastoxiv.page/@arXiv_csLG_bot/115575981129228810
- Deep Gaussian Process Proximal Policy Optimization
Matthijs van der Lende, Juan Cardenas-Cartagena
https://arxiv.org/abs/2511.18214 https://mastoxiv.page/@arXiv_csLG_bot/115610315210502140
- Spectral Concentration at the Edge of Stability: Information Geometry of Kernel Associative Memory
Akira Tamamori
https://arxiv.org/abs/2511.23083 https://mastoxiv.page/@arXiv_csLG_bot/115644325602130493
- xGR: Efficient Generative Recommendation Serving at Scale
Sun, Liu, Zhang, Wu, Yang, Liang, Li, Ma, Liang, Ren, Zhang, Liu, Zhang, Qian, Yang
https://arxiv.org/abs/2512.11529 https://mastoxiv.page/@arXiv_csLG_bot/115723008170311172
- Credit Risk Estimation with Non-Financial Features: Evidence from a Synthetic Istanbul Dataset
Atalay Denknalbant, Emre Sezdi, Zeki Furkan Kutlu, Polat Goktas
https://arxiv.org/abs/2512.12783 https://mastoxiv.page/@arXiv_csLG_bot/115729287232895097
- The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
Debu Sinha
https://arxiv.org/abs/2512.15068 https://mastoxiv.page/@arXiv_csLG_bot/115740048142898391
- Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library
Stritzel, H\"uhnerbein, Rauch, Zarate, Fleischmann, Buck, Lischka, Frey
https://arxiv.org/abs/2512.16715 https://mastoxiv.page/@arXiv_csLG_bot/115745910810427061
- Differentially private Bayesian tests
Abhisek Chakraborty, Saptati Datta
https://arxiv.org/abs/2401.15502 https://mastoxiv.page/@arXiv_statML_bot/111843467510507382
- SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
Paul Mangold, Sergey Samsonov, Safwan Labbi, Ilya Levin, Reda Alami, Alexey Naumov, Eric Moulines
https://arxiv.org/abs/2402.04114
- Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?
Guiomar Pescador-Barrios, Sarah Filippi, Mark van der Wilk
https://arxiv.org/abs/2408.07588 https://mastoxiv.page/@arXiv_statML_bot/112965266196097314
- Non-Perturbative Trivializing Flows for Lattice Gauge Theories
Mathis Gerdes, Pim de Haan, Roberto Bondesan, Miranda C. N. Cheng
https://arxiv.org/abs/2410.13161 https://mastoxiv.page/@arXiv_heplat_bot/113327593338897860
- Dynamic PET Image Prediction Using a Network Combining Reversible and Irreversible Modules
Sun, Zhang, Xia, Sun, Chen, Yang, Liu, Zhu, Liu
https://arxiv.org/abs/2410.22674 https://mastoxiv.page/@arXiv_eessIV_bot/113401026110345647
- Targeted Learning for Variable Importance
Xiaohan Wang, Yunzhe Zhou, Giles Hooker
https://arxiv.org/abs/2411.02221 https://mastoxiv.page/@arXiv_statML_bot/113429912435819479
- Refined Analysis of Federated Averaging and Federated Richardson-Romberg
Paul Mangold, Alain Durmus, Aymeric Dieuleveut, Sergey Samsonov, Eric Moulines
https://arxiv.org/abs/2412.01389 https://mastoxiv.page/@arXiv_statML_bot/113588027268311334
- Embedding-Driven Data Distillation for 360-Degree IQA With Residual-Aware Refinement
Abderrezzaq Sendjasni, Seif-Eddine Benkabou, Mohamed-Chaker Larabi
https://arxiv.org/abs/2412.12667 https://mastoxiv.page/@arXiv_csCV_bot/113672538318570349
- 3D Cell Oversegmentation Correction via Geo-Wasserstein Divergence
Peter Chen, Bryan Chang, Olivia A Creasey, Julie Beth Sneddon, Zev J Gartner, Yining Liu
https://arxiv.org/abs/2502.01890 https://mastoxiv.page/@arXiv_csCV_bot/113949981686723660
- DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents
Shashank Sharma, Janina Hoffmann, Vinay Namboodiri
https://arxiv.org/abs/2502.01956 https://mastoxiv.page/@arXiv_csRO_bot/113949997485625086
- Foundation for unbiased cross-validation of spatio-temporal models for species distribution modeling
Diana Koldasbayeva, Alexey Zaytsev
https://arxiv.org/abs/2502.03480
- GraphCompNet: A Position-Aware Model for Predicting and Compensating Shape Deviations in 3D Printing
Juheon Lee (Rachel), Lei (Rachel), Chen, Juan Carlos Catana, Hui Wang, Jun Zeng
https://arxiv.org/abs/2502.09652 https://mastoxiv.page/@arXiv_csCV_bot/114017924551186136
- LookAhead Tuning: Safer Language Models via Partial Answer Previews
Liu, Wang, Luo, Yuan, Sun, Liang, Zhang, Zhou, Hooi, Deng
https://arxiv.org/abs/2503.19041 https://mastoxiv.page/@arXiv_csCL_bot/114227502448008352
- Constraint-based causal discovery with tiered background knowledge and latent variables in single...
Christine W. Bang, Vanessa Didelez
https://arxiv.org/abs/2503.21526 https://mastoxiv.page/@arXiv_statML_bot/114238919468512990
toXiv_bot_toot

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow
Yike Zhu (Audio, Speech and Language Processing Group), Boyi Kang (The Hong Kong University of Science and Technology, Hong Kong, China, Audio, Speech and Language Processing Group), Ziqian Wang (Audio, Speech and Language Processing Group), Xingchen Li (Audio, Speech and Language Processing Group, Huawei Technologies, China), Zihan Zhang (Huawei Technologies, China), Wenjie Li (Huawei Technologies, China), Longshuai Xiao …

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow
Speech enhancement (SE) recovers clean speech from noisy signals and is vital for applications such as telecommunications and automatic speech recognition (ASR). While generative approaches achieve strong perceptual quality, they often rely on multi-step sampling (diffusion/flow-matching) or large language models, limiting real-time deployment. To mitigate these constraints, we present MeanFlowSE, a one-step generative SE framework. It adopts MeanFlow to predict an average-velocity field for on…

Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)
Nikita Kornilov, David Li, Tikhon Mavrin, Aleksei Leonov, Nikita Gushchin, Evgeny Burnaev, Iaroslav Koshelev, Alexander Korotin
https://arxiv.org/abs/2509.22459

Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)
While achieving exceptional generative quality, modern diffusion, flow, and other matching models suffer from slow inference, as they require many steps of iterative generation. Recent distillation methods address this by training efficient one-step generators under the guidance of a pre-trained teacher model. However, these methods are often constrained to only one specific framework, e.g., only to diffusion or only to flow models. Furthermore, these methods are naturally data-free, and to ben…

The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
Lina Conti, Dennis Fucci, Marco Gaido, Matteo Negri, Guillaume Wisniewski, Luisa Bentivogli
https://arxiv.org/abs/2509.26543 …

The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely regarded in explainable AI as more informative and interpretable than standard explanations. However, obtaining such explanations for speech-to-text (S2T) generative models remains an open challenge. Drawing from feature attribution techniques, we propose the first method to obtain contrastive explanations in S2T by analyzing how parts of the input spectrogram inf…

LLM4Rec: Large Language Models for Multimodal Generative Recommendation with Causal Debiasing
Bo Ma, Hang Li, ZeHua Hu, XiaoFan Gui, LuYao Liu, Simon Lau
https://arxiv.org/abs/2510.01622

LLM4Rec: Large Language Models for Multimodal Generative Recommendation with Causal Debiasing
Contemporary generative recommendation systems face significant challenges in handling multimodal data, eliminating algorithmic biases, and providing transparent decision-making processes. This paper introduces an enhanced generative recommendation framework that addresses these limitations through five key innovations: multimodal fusion architecture, retrieval-augmented generation mechanisms, causal inference-based debiasing, explainable recommendation generation, and real-time adaptive learni…

TempoControl: Temporal Attention Guidance for Text-to-Video Models
Shira Schiber, Ofir Lindenbaum, Idan Schwartz
https://arxiv.org/abs/2510.02226 https://a…

TempoControl: Temporal Attention Guidance for Text-to-Video Models
Recent advances in generative video models have enabled the creation of high-quality videos based on natural language prompts. However, these models frequently lack fine-grained temporal control, meaning they do not allow users to specify when particular visual elements should appear within a generated sequence. In this work, we introduce TempoControl, a method that allows for temporal alignment of visual concepts during inference, without requiring retraining or additional supervision. TempoCo…

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…

Permutation-Invariant Spectral Learning via Dyson Diffusion
Tassilo Schwarz, Cai Dieball, Constantin Kogler, Kevin Lam, Renaud Lambiotte, Arnaud Doucet, Alja\v{z} Godec, George Deligiannidis
https://arxiv.org/abs/2510.08535

Permutation-Invariant Spectral Learning via Dyson Diffusion
Diffusion models are central to generative modeling and have been adapted to graphs by diffusing adjacency matrix representations. The challenge of having up to $n!$ such representations for graphs with $n$ nodes is only partially mitigated by using permutation-equivariant learning architectures. Despite their computational efficiency, existing graph diffusion models struggle to distinguish certain graph families, unless graph data are augmented with ad hoc features. This shortcoming stems from…

Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley Synthesis
Junnuo Wang
https://arxiv.org/abs/2510.12175 https://

Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley Synthesis
Recent advances in diffusion-based generative models have enabled high-quality text-to-audio synthesis, but fine-grained acoustic control remains a significant challenge in open-source research. We present Audio Palette, a diffusion transformer (DiT) based model that extends the Stable Audio Open architecture to address this "control gap" in controllable audio generation. Unlike prior approaches that rely solely on semantic conditioning, Audio Palette introduces four time-varying control signal…

Chronologically Consistent Generative AI
Songrun He, Linying Lv, Asaf Manela, Jimmy Wu
https://arxiv.org/abs/2510.11677 https://arxiv.org/pdf/2510.11677

Chronologically Consistent Generative AI
We introduce a family of chronologically consistent, instruction-following large language models to eliminate lookahead bias. Each model is trained only on data available before a clearly defined knowledge-cutoff date, ensuring strict temporal separation from any post-cutoff data. The resulting framework offers (i) a simple, conversational chat interface, (ii) fully open, fixed model weights that guarantee replicability, and (iii) a conservative lower bound on forecast accuracy, isolating the s…

Reinforced Preference Optimization for Recommendation
Junfei Tan, Yuxin Chen, An Zhang, Junguang Jiang, Bin Liu, Ziru Xu, Han Zhu, Jian Xu, Bo Zheng, Xiang Wang
https://arxiv.org/abs/2510.12211

Reinforced Preference Optimization for Recommendation
Recent breakthroughs in large language models (LLMs) have fundamentally shifted recommender systems from discriminative to generative paradigms, where user behavior modeling is achieved by generating target items conditioned on historical interactions. Yet current generative recommenders still suffer from two core limitations: the lack of high-quality negative modeling and the reliance on implicit rewards. Reinforcement learning with verifiable rewards (RLVR) offers a natural solution by enabli…

Learning Robust Diffusion Models from Imprecise Supervision
Dong-Dong Wu, Jiacheng Cui, Wei Wang, Zhiqiang She, Masashi Sugiyama
https://arxiv.org/abs/2510.03016 https://…

Learning Robust Diffusion Models from Imprecise Supervision
Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably contain imprecise information in conditional inputs. Such supervision, often stemming from noisy, ambiguous, or incomplete labels, will cause condition mismatch and degrade generation quality. To address this challenge, we propose DMIS, a unified framework for training robust Diffusion Models from Imprecise Supervision, w…

Scalable In-context Ranking with Generative Models
Nilesh Gupta, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Inderjit Dhillon, Felix Yu
https://arxiv.org/abs/2510.05396 https…

Scalable In-context Ranking with Generative Models
In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). While it is effective, efficiency is a significant challenge in this paradigm, especially as the candidate list grows due to quadratic/super-linear scaling of attention operation with context length. To…

Fiaingen: A financial time series generative method matching real-world data quality
Jo\v{z}e M. Ro\v{z}anec, Tina \v{Z}ezlin, Laurentiu Vasiliu, Dunja Mladeni\'c, Radu Prodan, Dumitru Roman
https://arxiv.org/abs/2510.01169

Fiaingen: A financial time series generative method matching real-world data quality
Data is vital in enabling machine learning models to advance research and practical applications in finance, where accurate and robust models are essential for investment and trading decision-making. However, real-world data is limited despite its quantity, quality, and variety. The data shortage of various financial assets directly hinders the performance of machine learning models designed to trade and invest in these assets. Generative methods can mitigate this shortage. In this paper, we in…

Self-Speculative Masked Diffusions
Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet
https://arxiv.org/abs/2510.03929 https://arxiv.org/pdf/2…

Self-Speculative Masked Diffusions
We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked positions are then sampled, however, the factorization approximation means that sampling too many positions in one go leads to poor sample quality. As a result, many simulation steps and therefore n…

PolyGraph Discrepancy: a classifier-based metric for graph generation
Markus Krimmel, Philip Hartout, Karsten Borgwardt, Dexiong Chen
https://arxiv.org/abs/2510.06122 https://…

PolyGraph Discrepancy: a classifier-based metric for graph generation
Existing methods for evaluating graph generative models primarily rely on Maximum Mean Discrepancy (MMD) metrics based on graph descriptors. While these metrics can rank generative models, they do not provide an absolute measure of performance. Their values are also highly sensitive to extrinsic parameters, namely kernel and descriptor parametrization, making them incomparable across different graph descriptors. We introduce PolyGraph Discrepancy (PGD), a new evaluation framework that addresses…

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
Haoze Sun, Linfeng Jiang, Fan Li, Renjing Pei, Zhixin Wang, Yong Guo, Jiaqi Xu, Haoyu Chen, Jin Han, Fenglong Song, Yujiu Yang, Wenbo Li
https://arxiv.org/abs/2510.03012

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high computational cost and latency make them impractical for edge deployment. In this paper, we introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity. To achieve this, w…

Riemannian Consistency Model
Chaoran Cheng, Yusong Wang, Yuxin Chen, Xiangxin Zhou, Nanning Zheng, Ge Liu
https://arxiv.org/abs/2510.00983 https://arxiv.or…

Riemannian Consistency Model
Consistency models are a class of generative models that enable few-step generation for diffusion and flow matching models. While consistency models have achieved promising results on Euclidean domains like images, their applications to Riemannian manifolds remain challenging due to the curved geometry. In this work, we propose the Riemannian Consistency Model (RCM), which, for the first time, enables few-step consistency modeling while respecting the intrinsic manifold constraint imposed by th…

RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
Haozhe Jia, Wenshuo Chen, Xiucheng Wang, Nan Cheng, Hongbo Zhang, Kuimou Yu, Songning Lai, Nanjian Jia, Bowen Tian, Hongru Xiao, Yutao Yue
https://arxiv.org/abs/2510.09314

RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
Accurate and real-time radio map (RM) generation is crucial for next-generation wireless systems, yet diffusion-based approaches often suffer from large model sizes, slow iterative denoising, and high inference latency, which hinder practical deployment. To overcome these limitations, we propose \textbf{RadioFlow}, a novel flow-matching-based generative framework that achieves high-fidelity RM generation through single-step efficient sampling. Unlike conventional diffusion models, RadioFlow lea…

Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report
Riccardo Mereu, Aidan Scannell, Yuxin Hou, Yi Zhao, Aditya Jitta, Antonio Dominguez, Luigi Acerbi, Amos Storkey, Paul Chang
https://arxiv.org/abs/2510.07092

Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report
World models are a powerful paradigm in AI and robotics, enabling agents to reason about the future by predicting visual observations or compact latent states. The 1X World Model Challenge introduces an open-source benchmark of real-world humanoid interaction, with two complementary tracks: sampling, focused on forecasting future image frames, and compression, focused on predicting future discrete latent codes. For the sampling track, we adapt the video generation foundation model Wan-2.2 TI2V-…

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…

Bidirectional Representations Augmented Autoregressive Biological Sequence Generation:Application in De Novo Peptide Sequencing
Xiang Zhang, Jiaqi Wei, Zijie Qiu, Sheng Xu, Zhi Jin, ZhiQiang Gao, Nanqing Dong, Siqi Sun
https://arxiv.org/abs/2510.08169

Bidirectional Representations Augmented Autoregressive Biological Sequence Generation:Application in De Novo Peptide Sequencing
Autoregressive (AR) models, common in sequence generation, are limited in many biological tasks such as de novo peptide sequencing and protein modeling by their unidirectional nature, failing to capture crucial global bidirectional token dependencies. Non-Autoregressive (NAR) models offer holistic, bidirectional representations but face challenges with generative coherence and scalability. To transcend this, we propose a hybrid framework enhancing AR generation by dynamically integrating rich c…

Test-Time Anchoring for Discrete Diffusion Posterior Sampling
Litu Rout, Andreas Lugmayr, Yasamin Jafarian, Srivatsan Varadharajan, Constantine Caramanis, Sanjay Shakkottai, Ira Kemelmacher-Shlizerman
https://arxiv.org/abs/2510.02291

Test-Time Anchoring for Discrete Diffusion Posterior Sampling
We study the problem of posterior sampling using pretrained discrete diffusion foundation models, aiming to recover images from noisy measurements without retraining task-specific models. While diffusion models have achieved remarkable success in generative modeling, most advances rely on continuous Gaussian diffusion. In contrast, discrete diffusion offers a unified framework for jointly modeling categorical data such as text and images. Beyond unification, discrete diffusion provides faster i…

Efficient Bayesian Inference from Noisy Pairwise Comparisons
Till Aczel, Lucas Theis, Wattenhofer Roger
https://arxiv.org/abs/2510.09333 https://arxiv.org/…

Efficient Bayesian Inference from Noisy Pairwise Comparisons
Evaluating generative models is challenging because standard metrics often fail to reflect human preferences. Human evaluations are more reliable but costly and noisy, as participants vary in expertise, attention, and diligence. Pairwise comparisons improve consistency, yet aggregating them into overall quality scores requires careful modeling. Bradley-Terry-based methods update item scores from comparisons, but existing approaches either ignore rater variability or lack convergence guarantees,…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/7]:
- Calibrating Generative Models
Henry D. Smith, Nathaniel L. Diamant, Brian L. Trippe

Distilled Protein Backbone Generation
Liyang Xie, Haoran Zhang, Zhendong Wang, Wesley Tansey, Mingyuan Zhou
https://arxiv.org/abs/2510.03095 https://arxiv.…

Distilled Protein Backbone Generation
Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unprecedented capabilities for de novo protein design. However, while achieving notable performance in generation quality, these models are limited by their generating speed, often requiring hundreds of iterative steps in the reverse-diffusion process. This computational bottleneck limits their practical utility in large-scale protein discovery, where thousand…