Generative Adversarial Networks and Image Synthesis

Neueste Paper

• PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics

  Xueyu Luan, Chenwei Shi · 19. Mai 2026

  World models built on recurrent state space architectures enable efficient latent imagination, yet remain physically unstructured, producing dynamics that violate conservation and dissipative principles. We introduce a unified Port-Hamiltonian framework that remedies this through three synergistic m…

• Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling

  Tianyue Yang, Sandro Tacchella, Xiao Xue · 19. Mai 2026

  Understanding galaxy morphology evolution across cosmic time requires models that can generate realistic galaxy populations conditioned on redshift. In this work, we study efficient redshift-conditioned generative modeling for astrophysical image synthesis using diffusion models and pixel-MeanFlow. …

• Content-Style Identification via Differential Independence

  Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha, Xiao Fu · 19. Mai 2026

  Generative analysis often models multi-domain observations as nonlinear mixtures of domain-invariant content variables and domain-specific style variables. Identifying both factors from unpaired domains enables tasks such as domain transfer and counterfactual data generation. Prior work establishes …

• Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling

  Afiq Abdillah Effiezal Aswadi, Oliver Britton, Ross Baker, Matthew Farrugia-Roberts · 19. Mai 2026

  Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning problems involve data distributions that change throughout training. How does such non-stationarity impact the inductive biases of deep learning towards …

• Position: Weight Space Should Be a First-Class Generative AI Modality

  Zhangyang Wang, Peihao Wang, Kai Wang · 19. Mai 2026

  Neural network checkpoints have quietly become a large-scale data resource: millions of trained weight vectors now exist, each encoding task-, domain-, and architecture-specific knowledge. This position paper argues that model checkpoints should be treated as a first-class data modality, and that ge…

• Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives

  Santosh Premi · 19. Mai 2026

  Joint-Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised video representation learning, yet the behavior of auxiliary objectives in small-scale Video-JEPA training is not well characterized. We report a small-scale empirical study of 18 auxiliary objective varian…

• PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting

  Yangyou Liu, Zezhi Shao, Xinyu Chen, Hu Chen, Fei Wang, Yuankai Wu · 19. Mai 2026

  Time series forecasting under non-stationarity faces a fundamental tension between capturing stable representations and adapting to distribution shifts. Existing methods implicitly rely on static historical assumptions, leading to a critical failure mode we term Phase Amnesia, where models become bl…

• TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates

  Meysam Alishahi, Yan Zheng, Junpeng Wang, Chin-Chia Michael Yeh, Jeff M. Phillips · 19. Mai 2026

  Tabular data generation considers a large table with multiple columns -- each column comprised of numerical, categorical, or sometimes ordinal values. The goal is to produce new rows for the table that replicate the distribution of rows from the original data -- without just copying those initial ro…

• Divergence-Suppressing Couplings for Rectified Flow

  Yimeng Min, Carla P. Gomes · 19. Mai 2026

  The promise of Rectified Flow rests on producing self-generated couplings whose trajectories are straight, or nearly so. In practice, trajectories generated by the base flow model can bend and intertwine, and the resulting coupling inherits this distortion. In this paper, we identify that such traje…

• A Simplex Witness Certificate for Constant Collapse in Variational Autoencoders

  Zegu Zhang, Jianhua Peng, Jian Zhang · 19. Mai 2026

  This note studies exact constant collapse in variational autoencoders, where the encoder mean becomes independent of the input. The goal is to make this specific failure mode pre-designable, monitorable during training, and certifiable after training. The prior is kept as the standard Gaussian. Give…

• Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)

  Micha{\l} Brzozowski, Neo Christopher Chung · 19. Mai 2026

  Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large fraction of features are never activated and are unstable. Despit…

• Improved Baselines with Representation Autoencoders

  Jaskirat Singh, Boyang Zheng, Zongze Wu, Richard Zhang, Eli Shechtman, Saining Xie · 19. Mai 2026

  Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insights which simplify and improve RAE. First, we study a generalized formulation where the representation is defined as sum …

• MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation

  Yu Chang, Jiahao Chen, Anzhe Cheng, Paul Bogdan · 19. Mai 2026

  Diffusion models have achieved strong results in text-to-image generation, but important limitations remain as prompts become more structured and multi-object. On the architecture side, U-Net backbones are efficient and stable, yet their locality makes global coordination harder, while Transformer-b…

• StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow

  Gurjeet Jagwani, Stephen Thorp, Sinan Deger, Hiranya Peiris · 19. Mai 2026

  Diffusion and flow-based models are ubiquitously used for generative modelling and density estimation. They admit a deterministic probability flow ordinary differential equation (PF-ODE), analogous to continuous normalizing flows (CNFs), which describes the transport of the probability mass. Obtaini…

• Genflow Ad Studio: A Compound AI Architecture for Brand-Aligned, Self-Correcting Video Generation

  Debanshu Das, Lavi Nigam, Sunil Kumar Jang Bahadur, Gopala Dhar · 19. Mai 2026

  Recent advancements in generative video models demonstrate high visual fidelity, yet their integration into enterprise environments is restricted by temporal inconsistencies and severe brand misalignment. Current monolithic architectures struggle to enforce rigid brand constraints, frequently halluc…

• A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows

  Chenguang Wang, Tianshu Yu · 19. Mai 2026

  We develop a unified theoretical framework for data-free one-step sampling from unnormalized target distributions based on Wasserstein gradient flows. For a broad class of standard f-divergence objectives, we show that the induced velocity field admits the universal form $\mathbf{V}(x)=w(r(x))\,\bet…

• The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation

  Ninad Joshi, Ashutosh Ranjan, Vivek Srivastava, Shirish Karande · 19. Mai 2026

  Generative text-to-image models are typically trained on large-scale web-scraped datasets that include diverse visual content such as copyrighted and stylistically distinctive artworks, raising concerns about ownership, attribution, and the unintended reuse of protected visual expressions. A key iss…

• Venom: A PyTorch Generative Modeling Toolkit

  Liang Yan · 19. Mai 2026

  Modern generative modeling has grown into a broad collection of related but often separately implemented paradigms, including denoising diffusion models, score-based stochastic differential equations, flow matching, variational autoencoders, normalizing flows, adversarial models, and energy-based mo…

• Flowing with Confidence

  Friso de Kruiff, Dario Coscia, Max Welling, Erik Bekkers · 19. Mai 2026

  Generative models can produce nonsensical text, unrealistic images, and unstable materials faster than simulation or human review can absorb; without per-sample confidence, trust erodes. Existing fixes run $k$ ensembles or stochastic trajectories at $k\times$ compute, measuring variability between m…

• Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network

  Grigory Bartosh, David Ruhe, Emiel Hoogeboom, Jonathan Heek, Thomas Mensink, Tim Salimans · 19. Mai 2026

  Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network. In this work, we propose Dual-Rate Diffusion, a method to accelerate sampling by interleaving the execution of a heavy …

• Learning Unbiased Permutations via Flow Matching

  Yimeng Min, Carla P. Gomes · 19. Mai 2026

  Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a conditional flow matching framework that operates directly on the …

• Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

  Joan Serr\`a, Dipam Goswami, Fabio Morreale, Wei-Hsiang Liao, Yuki Mitsufuji · 19. Mai 2026

  Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliability and robustness, preventing their adoption in real-world setups. In this paper, we take a decisive step towards more r…

• Probing for Representation Manifolds in Superposition

  Alexander Modell · 19. Mai 2026

  This paper introduces the Manifold Probe, a supervised method for discovering representation manifolds in superposition. The method generalizes linear regression probes by learning the space of features of a concept that can be linearly predicted from the representations, and then learning the direc…

• SAS: Semantic-aware Sampling for Generative Dataset Distillation

  Mingzhuo Li, Guang Li, Linfeng Ye, Jiafeng Mao, Takahiro Ogawa, Konstantinos N. Plataniotis, Miki Haseyama · 19. Mai 2026

  Deep neural networks have achieved impressive performance across a wide range of tasks, but this success often comes with substantial computational and storage costs due to large-scale training data. Dataset distillation addresses this challenge by constructing compact yet informative datasets that …

• Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures

  Chenyang Wang, Weizhong Wang, Yinuo Ren, Jose Blanchet, Yiping Lu · 19. Mai 2026

  iffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations, introducing bias, high comput…