Generative Adversarial Networks and Image Synthesis

Neueste Paper

• End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

  Wenda Chu, Bingliang Zhang, Jiaqi Han, Yizhuo Li, Linjie Yang, Yisong Yue, Qiushan Guo · 4. Mai 2026

  Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with …

• Binomial flows: Denoising and flow matching for discrete ordinal data

  Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti · 4. Mai 2026

  Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, this relation has been largely missing in the discrete setting where common approaches focus on learning discrete scores an…

• Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows

  Gitte Kremling, Jeffrey N\"af, Johannes Lederer · 4. Mai 2026

  The prevalence of missing values in data science poses a substantial risk to any further analyses. Despite a wealth of research, principled nonparametric methods to deal with general non-monotone missingness are still scarce. Instead, ad-hoc imputation methods are often used, for which it remains un…

• Caracal: Causal Architecture via Spectral Mixing

  Bingzheng Gan, Tianyi Zhang, Yusu Li, Jing Huang, Wei Shi, Yangkai Ding, Tao Yu · 4. Mai 2026

  The scalability of Large Language Models to long sequences is hindered by the quadratic cost of attention and the limitations of positional encodings. To address these, we introduce Caracal, a novel architecture that replaces attention with a parameter-efficient, $\mathcal{O}(L \log L)$ Multi-Head F…

• Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision

  Jiali Cui, Zhiqiang Lao, Heather Yu · 4. Mai 2026

  Energy-based models (EBMs) are a flexible class of deep generative models and are well-suited to capture complex dependencies in multimodal data. However, learning multimodal EBM by maximum likelihood requires Markov Chain Monte Carlo (MCMC) sampling in the joint data space, where noise-initialized …

• It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models

  Anne Harrington, A. Sophia Koepke, Shyamgopal Karthik, Trevor Darrell, Alexei A. Efros · 4. Mai 2026

  Contemporary text-to-image models exhibit a surprising degree of mode collapse, as can be seen when sampling several images given the same text prompt. Previous work has attempted to address this issue by steering the model using guidance mechanisms, or by generating a large pool of candidates and r…

• Brain MR Image Synthesis with 3D Multi-Contrast Self-Attention GAN

  Zaid A. Abod, Furqan Aziz · 4. Mai 2026

  Complete and high-quality multi-modal Magnetic Resonance Imaging (MRI) is essential for accurate neuro-oncological assessment, as each contrast provides complementary anatomical and pathological information. However, acquiring all modalities (e.g., T1c, T1n, T2w, T2f) for every patient is often impr…

• Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

  Sen Cui, Jingheng Ma · 4. Mai 2026

  World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world model research is often dominated by three partially separated routes: 2D video-generative models that emphasize visual …

• When Do Diffusion Models learn to Generate Multiple Objects?

  Yujin Jeong, Arnas Uselis, Iro Laina, Seong Joon Oh, Anna Rohrbach · 4. Mai 2026

  Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disen…

• Latent Generative Modeling of Random Fields from Limited Training Data

  James E. Warner, Tristan A. Shah, Patrick E. Leser, Geoffrey F. Bomarito, Joshua D. Pribe, Michael C. Stanley · 4. Mai 2026

  The ability to accurately model random fields plays a critical role in science and engineering for problems involving uncertain, spatially-varying quantities such as heterogeneous material properties and turbulent flows. Deep generative models offer a powerful tool for sampling high- or infinite-dim…

• EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure

  Zihao Ding, Beining Wu, Jun Huang · 4. Mai 2026

  Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint embedding training entangles forgotten knowledge across both modalities and client gradient subspaces, hindering federated unlearning. Previous feder…

• CollaFuse: Collaborative Diffusion Models

  Simeon Allmendinger, Domenique Zipperling, Lukas Struppek, Niklas K\"uhl · 4. Mai 2026

  In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly concerning data availability, computational requirements, and privac…

• Man, Machine, and Mathematics

  Akshunna S. Dogra · 1. Mai 2026

  Nonlinear models and optimization methods have successfully tackled a rapidly growing set of problems in recent years. Indeed, a relatively small toolbox of such models and methods can provide sufficient performance across a large landscape of tasks: deep learning alone has made significant recent c…

• Sampler-Robust Optimization under Generative Models

  Ziwei Zhang, Jonathan Yu-Meng Li · 1. Mai 2026

  Modern stochastic optimization pipelines increasingly rely on learned generative models to represent uncertainty, while downstream decisions are evaluated almost entirely through Monte Carlo scenarios. This shifts the operational object of uncertainty from an explicit probability law to the sampler …

• How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

  Jerry Y. Huang, Justin Lin, Sheel Shah, Kartik Nair, Nicholas M. Boffi · 1. Mai 2026

  In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as guidance. Despite their widespread use, existing guidance methods either require expensive multi-particle, many-step scheme…

• Preserving Temporal Dynamics in Time Series Generation

  Ci Lin, Futong Li, Tet Yeap, Iluju Kiringa · 1. Mai 2026

  Time-series data augmentation plays a crucial role in regression-oriented forecasting tasks, where limited data restricts the performance of deep learning models. While Generative Adversarial Networks (GANs) have shown promise in synthetic time-series generation, existing approaches primarily focus …

• VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference

  Sakshi Agarwal, Gabriel Hope, Jimin Heo, Erik B. Sudderth · 1. Mai 2026

  Diffusion probabilistic models learn to remove noise added during training, generating novel data (e.g., images) from Gaussian noise through sequential denoising. However, conditioning the generative process on corrupted or masked images is challenging. While various methods have been proposed for i…

• ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space

  Gabe Guo, Thanawat Sornwanee, Lutong Hao, Elon Litman, Stefano Ermon, Jose Blanchet · 1. Mai 2026

  Generating continuous-time, continuous-space stochastic processes (e.g., videos, weather forecasts) conditioned on partial observations (e.g., first and last frames) is a fundamental challenge. Existing approaches, (e.g., diffusion models), suffer from key limitations: (1) noise-to-data evolution fa…

• AdvDMD: Adversarial Reward Meets DMD For High-Quality Few-Step Generation

  Xu Wang, Zexian Li, Litong Gong, Tiezheng Ge, Zhijie Deng · 1. Mai 2026

  Diffusion models offer superior generation quality at the expense of extensive sampling steps. Distillation methods, with Distribution Matching Distillation (DMD) as a popular example, can mitigate this issue, but performance degradation remains pronounced when sampling steps are limited. Reinfo…

• Culture-inspired Multi-modal Color Palette Generation and Colorization: A Chinese Youth Subculture Case

  Yufan Li, Jinggang Zhuo, Ling Fan, Harry Jiannan Wang · 1. Mai 2026

  Color is an essential component of graphic design, acting not only as a visual factor but also carrying cultural implications. However, existing research on algorithmic color palette generation and colorization largely ignores the cultural aspect. In this paper, we contribute to this line of researc…

• Simple Self-Conditioning Adaptation for Masked Diffusion Models

  Michael Cardei, Huu Binh Ta, Ferdinando Fioretto · 1. Mai 2026

  Masked diffusion models (MDMs) generate discrete sequences by iterative denoising under an absorbing masking process. In standard masked diffusion, if a token remains masked after a reverse update, the model discards its clean-state prediction for that position. Thus, still-masked positions must be …

• PhyCo: Learning Controllable Physical Priors for Generative Motion

  Sriram Narayanan, Ziyu Jiang, Srinivasa Narasimhan, Manmohan Chandraker · 1. Mai 2026

  Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and ph…

• GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

  Ziyue Zeng, Xun Su, Haoyuan Liu, Bingyu Lu, Yui Tatsumi, Hiroshi Watanabe · 1. Mai 2026

  At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in which a pretrained video generative model serves directly as…

• ViPO: Visual Preference Optimization at Scale

  Ming Li, Jie Wu, Justin Cui, Xiaojie Li, Rui Wang, Chen Chen · 30. April 2026

  While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where winners excel in some dimensions but underperform in others. Naiv…

• Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection

  Jaskirat Sudan, Hashim Ali, Surya Subramani, Hafiz Malik · 30. April 2026

  Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipelines; however, the focus on SupCon itself is missing. In this work, we run a contro…