Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Synthetic Time Series Generation via Complex Networks

  Jaime Vale, Vanessa Freitas Silva, Maria Eduarda Silva, Fernando Silva · 2. Februar 2026

  Time series data are essential for a wide range of applications, particularly in developing robust machine learning models. However, access to high-quality datasets is often limited due to privacy concerns, acquisition costs, and labeling challenges. Synthetic time series generation has emerged as a…

• Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing

  Yilong Huang, Songze Li · 2. Februar 2026

  Diffusion-based face swapping achieves state-of-the-art performance, yet it also exacerbates the potential harm of malicious face swapping to violate portraiture right or undermine personal reputation. This has spurred the development of proactive defense methods. However, existing approaches face a…

• Unsupervised Synthetic Image Attribution: Alignment and Disentanglement

  Zongfang Liu, Guangyi Chen, Boyang Sun, Tongliang Liu, Kun Zhang · 2. Februar 2026

  As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring model transparency. Existing methods achieve this attribution goal by training models using annotated pairs of synthetic i…

• Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features

  Markus Mueller, Kathrin Gruber, Dennis Fok · 2. Februar 2026

  Advances in generative modeling have recently been adapted to tabular data containing discrete and continuous features. However, generating mixed-type features that combine discrete states with an otherwise continuous distribution in a single feature remains challenging. We advance the state-of-the-…

• Decoupled Diffusion Sampling for Inverse Problems on Function Spaces

  Thomas Y. L. Lin, Jiachen Yao, Lufang Chiang, Julius Berner, Anima Anandkumar · 2. Februar 2026

  We propose a data-efficient, physics-aware generative framework in function space for inverse PDE problems. Existing plug-and-play diffusion posterior samplers represent physics implicitly through joint coefficient-solution modeling, requiring substantial paired supervision. In contrast, our Decoupl…

• Generative and Nonparametric Approaches for Conditional Distribution Estimation: Methods, Perspectives, and Comparative Evaluations

  Yen-Shiu Chin, Zhi-Yu Jou, Toshinari Morimoto, Chia-Tse Wang, Ming-Chung Chang, Tso-Jung Yen, Su-Yun Huang, Tailen Hsing · 2. Februar 2026

  The inference of conditional distributions is a fundamental problem in statistics, essential for prediction, uncertainty quantification, and probabilistic modeling. A wide range of methodologies have been developed for this task. This article reviews and compares several representative approaches sp…

• Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector

  Wenqiang Zu, Shenghao Xie, Bo Lei, Lei Ma · 2. Februar 2026

  Recent progress in generative modeling has enabled high-quality visual synthesis with diffusion-based frameworks, supporting controllable sampling and large-scale training. Inference-time guidance methods such as classifier-free and representative guidance enhance semantic alignment by modifying sam…

• GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning

  Naoki Murata, Yuhta Takida, Chieh-Hsin Lai, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji · 2. Februar 2026

  Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners often need group-level answers (e.g., artistic styles or object classes). Group-wise attribution is counterfactual: how w…

• MoVE: Mixture of Value Embeddings -- A New Axis for Scaling Parametric Memory in Autoregressive Models

  Yangyan Li · 2. Februar 2026

  Autoregressive sequence modeling stands as the cornerstone of modern Generative AI, powering results across diverse modalities ranging from text generation to image generation. However, a fundamental limitation of this paradigm is the rigid structural coupling of model capacity to computational cost…

• Gradual Fine-Tuning for Flow Matching Models

  Gudrun Thorkelsdottir, Arindam Banerjee · 2. Februar 2026

  Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or strict efficiency demands, where unconstrained fine-tuning can erode the accuracy and efficiency gains learned during pretraining. Prior work has produced theoretical guarantees and empi…

• Manifold-Aware Perturbations for Constrained Generative Modeling

  Katherine Keegan, Lars Ruthotto · 2. Februar 2026

  Generative models have enjoyed widespread success in a variety of applications. However, they encounter inherent mathematical limitations in modeling distributions where samples are constrained by equalities, as is frequently the setting in scientific domains. In this work, we develop a computationa…

• How well do generative models solve inverse problems? A benchmark study

  Patrick Kr\"uger, Patrick Materne, Werner Krebs, Hanno Gottschalk · 2. Februar 2026

  Generative learning generates high dimensional data based on low dimensional conditions, also called prompts. Therefore, generative learning algorithms are eligible for solving (Bayesian) inverse problems. In this article we compare a traditional Bayesian inverse approach based on a forward regressi…

• A Random Matrix Theory of Masked Self-Supervised Regression

  Arie Wortsman Zurich, Federica Gerace, Bruno Loureiro, Yue M. Lu · 2. Februar 2026

  In the era of transformer models, masked self-supervised learning (SSL) has become a foundational training paradigm. A defining feature of masked SSL is that training aggregates predictions across many masking patterns, giving rise to a joint, matrix-valued predictor rather than a single vector-valu…

• Corrected Samplers for Discrete Flow Models

  Zhengyan Wan, Yidong Ouyang, Liyan Xie, Fang Fang, Hongyuan Zha, Guang Cheng · 2. Februar 2026

  Discrete flow models (DFMs) have been proposed to learn the data distribution on a finite state space, offering a flexible framework as an alternative to discrete diffusion models. A line of recent work has studied samplers for discrete diffusion models, such as tau-leaping and Euler solver. However…

• Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation

  Qidong Yang, Qianyu Julie Zhu, Jonathan Giezendanner, Youssef Marzouk, Stephen Bates, Sherrie Wang · 2. Februar 2026

  Conditional generative models map input variables to complex, high-dimensional distributions, enabling realistic sample generation in a diverse set of domains. A critical challenge with these models is the absence of calibrated uncertainty, which undermines trust in individual outputs for high-stake…

• Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity

  Jianhao Huang, Baharan Mirzasoleiman · 2. Februar 2026

  Masked Diffusion Language Models have recently emerged as a powerful generative paradigm, yet their generalization properties remain understudied compared to their auto-regressive counterparts. In this work, we investigate these properties within the setting of the $k$-parity problem (computing the …

• Latent Iterative Refinement Flow: A Geometric Constrained Approach for Few-Shot Generation

  Songtao Li, Tianqi Hou, Zhenyu Liao, Ting Gao · 2. Februar 2026

  Diffusion and flow-matching models trained with limited data often tend to memorize the training data instead of generalization, leading to severely reduced diversity. In this paper, we provide a dynamical perspective and identify this ``collapse-to-memorization'' phenomenon as a consequence of the …

• SpanNorm: Reconciling Training Stability and Performance in Deep Transformers

  Chao Wang, Bei Li, Jiaqi Zhang, Xinyu Liu, Yuchun Fan, Linkun Lyu, Xin Chen, Jingang Wang, Tong Xiao, Peng Pei, Xunliang Cai · 2. Februar 2026

  The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture ensures training stability at the cost of potential perform…

• OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation

  Jin Li, Tao Chen, Shuai Jiang, Weijie Wang, Jingwen Luo, Chenhui Wu · 2. Februar 2026

  Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail …

• Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models

  Francisco Caetano, Christiaan Viviers, Peter H. N. De With, Fons van der Sommen · 2. Februar 2026

  Flow Matching has emerged as a powerful framework for learning continuous transformations between distributions, enabling high-fidelity generative modeling. This work introduces Symmetrical Flow Matching (SymmFlow), a new formulation that unifies semantic segmentation, classification, and image gene…

• DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation

  Hun Chang, Byunghee Cha, Jong Chul Ye · 2. Februar 2026

  Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generative performance. Unfortunately, existing approaches often suffer from limited reconstruction fidelity due to the loss of high-frequency details. In this work,…

• SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models

  Mingyu Lu, Soham Gadgil, Chris Lin, Chanwoo Kim, Su-In Lee · 2. Februar 2026

  As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces. While the Shapley value offers a theoretically ground…

• Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization

  Wang Yuanchao, Lai Zhao-Rong, Zhong Tianqi, Li Fengnan · 2. Februar 2026

  Out-of-distribution (OOD) generalization remains challenging when models simultaneously encounter correlation shifts across environments and diversity shifts driven by rare or hard samples. Existing invariant risk minimization (IRM) methods primarily address spurious correlations at the environment …

• SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants

  Santanu Subhash Rathod, Pietro Li\`o, Xiao Zhang · 2. Februar 2026

  Flow matching is a scalable generative framework for characterizing continuous normalizing flows with wide-range applications. However, current state-of-the-art methods are not well-suited for modeling dynamical systems, as they construct conditional paths using linear interpolants that may not capt…

• OneFlowSBI: One Model, Many Queries for Simulation-Based Inference

  Mayank Nautiyal, Li Ju, Melker Ernfors, Klara Hagland, Ville Holma, Maximilian Werk\"o S\"oderholm, Andreas Hellander, Prashant Singh · 2. Februar 2026

  We introduce \textit{OneFlowSBI}, a unified framework for simulation-based inference that learns a single flow-matching generative model over the joint distribution of parameters and observations. Leveraging a query-aware masking distribution during training, the same model supports multiple inferen…