Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Generative Adversarial Gumbel MCTS for Abstract Visual Composition Generation

  Zirui Zhao, Boye Niu, David Hsu, Wee Sun Lee · 2. Dezember 2025

  We study abstract visual composition, in which identity is primarily determined by the spatial configuration and relations among a small set of geometric primitives (e.g., parts, symmetry, topology). They are invariant primarily to texture and photorealistic detail. Composing such structures from fi…

• Diffusion Model in Latent Space for Medical Image Segmentation Task

  Huynh Trinh Ngoc, Toan Nguyen Hai, Ba Luong Son, Long Tran Quoc · 2. Dezember 2025

  Medical image segmentation is crucial for clinical diagnosis and treatment planning. Traditional methods typically produce a single segmentation mask, failing to capture inherent uncertainty. Recent generative models enable the creation of multiple plausible masks per image, mimicking the collaborat…

• Improved Mean Flows: On the Challenges of Fastforward Generative Models

  Zhengyang Geng, Yiyang Lu, Zongze Wu, Eli Shechtman, J. Zico Kolter, Kaiming He · 2. Dezember 2025

  MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training objective and the guidance mechanism. First, the original MF's training target depends not only on the underlying ground-tru…

• ToMA: Token Merge with Attention for Diffusion Models

  Wenbo Lu, Shaoyi Zheng, Yuxuan Xia, Shengjie Wang · 2. Dezember 2025

  Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like ToMeSD and ToFu reduce FLOPs by merging redundant tokens in generated images but rely on GPU-inefficient operations (e.…

• CORAL: Disentangling Latent Representations in Long-Tailed Diffusion

  Esther Rodriguez, Monica Welfert, Samuel McDowell, Nathan Stromberg, Julian Antolin Camarena, Lalitha Sankar · 2. Dezember 2025

  Diffusion models have achieved impressive performance in generating high-quality and diverse synthetic data. However, their success typically assumes a class-balanced training distribution. In real-world settings, multi-class data often follow a long-tailed distribution, where standard diffusion mod…

• SVRG and Beyond via Posterior Correction

  Nico Daheim, Thomas M\"ollenhoff, Ming Liang Ang, Mohammad Emtiyaz Khan · 2. Dezember 2025

  Stochastic Variance Reduced Gradient (SVRG) and its variants aim to speed-up training by using gradient corrections, but have seen limited success in deep learning. Here, we show surprising new foundational connections of SVRG to a recently proposed Bayesian method called posterior correction. Speci…

• Deconstructing Generative Diversity: An Information Bottleneck Analysis of Discrete Latent Generative Models

  Yudi Wu, Wenhao Zhao, Dianbo Liu · 2. Dezember 2025

  Generative diversity varies significantly across discrete latent generative models such as AR, MIM, and Diffusion. We propose a diagnostic framework, grounded in Information Bottleneck (IB) theory, to analyze the underlying strategies resolving this behavior. The framework models generation as a con…

• Weight Space Representation Learning with Neural Fields

  Zhuoqian Yang, Mathieu Salzmann, Sabine S\"usstrunk · 2. Dezember 2025

  In this work, we investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruct…

• Hyperparameters are all you need: Using five-step inference for an original diffusion model to generate images comparable to the latest distillation model

  Zilai Li · 2. Dezember 2025

  The diffusion model is a state-of-the-art generative model that samples images by applying a neural network iteratively. However, the original sampling algorithm requires substantial computation cost, and reducing the sampling step is a prevailing research area. To cope with this problem, one mainst…

• VIVAT: Virtuous Improving VAE Training through Artifact Mitigation

  Lev Novitskiy, Viacheslav Vasilev, Maria Kovaleva, Vladimir Arkhipkin, Denis Dimitrov · 2. Dezember 2025

  Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation quality. This paper introduces VIVAT, a systematic approach to mitigating common artifacts in KL-VAE training without requir…

• In Search of Adam's Secret Sauce

  Antonio Orvieto, Robert M. Gower · 2. Dezember 2025

  Understanding the remarkable efficacy of Adam when training transformer-based language models has become a central research topic within the optimization community. To gain deeper insights, several simplifications of Adam have been proposed, such as the signed gradient and signed momentum methods. I…

• Adaptive-lambda Subtracted Importance Sampled Scores in Machine Unlearning for DDPMs and VAEs

  MohammadParsa Dini, Human Jafari, Sajjad Amini, MohammadMahdi Mojahedian · 2. Dezember 2025

  Machine Unlearning is essential for large generative models (VAEs, DDPMs) to comply with the right to be forgotten and prevent undesired content generation without costly retraining. Existing approaches, such as Static-lambda SISS for diffusion models, rely on a fixed mixing weight lambda, which is …

• Preventing Model Collapse via Contraction-Conditioned Neural Filters

  Zongjian Han, Yiran Liang, Ruiwen Wang, Yiwei Luo, Yilin Huang, Xiaotong Song, Dongqing Wei · 2. Dezember 2025

  This paper presents a neural network filter method based on contraction operators to address model collapse in recursive training of generative models. Unlike \cite{xu2024probabilistic}, which requires superlinear sample growth ($O(t^{1+s})$), our approach completely eliminates the dependence on inc…

• Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer

  Dong In Lee, Hyungjun Doh, Seunggeun Chi, Runlin Duan, Sangpil Kim, Karthik Ramani · 2. Dezember 2025

  Recent progress in 4D representations, such as Dynamic NeRF and 4D Gaussian Splatting (4DGS), has enabled dynamic 4D scene reconstruction. However, text-driven 4D scene editing remains under-explored due to the challenge of ensuring both multi-view and temporal consistency across space and time duri…

• RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards

  Junyan Ye, Leiqi Zhu, Yuncheng Guo, Dongzhi Jiang, Zilong Huang, Yifan Zhang, Zhiyuan Yan, Haohuan Fu, Conghui He, Weijia Li · 2. Dezember 2025

  With the continuous advancement of image generation technology, advanced models such as GPT-Image-1 and Qwen-Image have achieved remarkable text-to-image consistency and world knowledge However, these models still fall short in photorealistic image generation. Even on simple T2I tasks, they tend to …

• FR-TTS: Test-Time Scaling for NTP-based Image Generation with Effective Filling-based Reward Signal

  Hang Xu, Linjiang Huang, Feng Zhao · 2. Dezember 2025

  Test-time scaling (TTS) has become a prevalent technique in image generation, significantly boosting output quality by expanding the number of parallel samples and filtering them using pre-trained reward models. However, applying this powerful methodology to the next-token prediction (NTP) paradigm …

• USB: Unified Synthetic Brain Framework for Bidirectional Pathology-Healthy Generation and Editing

  Jun Wang, Peirong Liu · 2. Dezember 2025

  Understanding the relationship between pathological and healthy brain structures is fundamental to neuroimaging, connecting disease diagnosis and detection with modeling, prediction, and treatment planning. However, paired pathological-healthy data are extremely difficult to obtain, as they rely on …

• OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion

  Sai Koneru, Matthias Huck, Jan Niehues · 2. Dezember 2025

  There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only used in cascaded pipelines for speech translation (ST), performing automatic speech recognition first followed by transla…

• Art2Music: Generating Music for Art Images with Multi-modal Feeling Alignment

  Jiaying Hong, Ting Zhu, Thanet Markchom, Huizhi Liang · 2. Dezember 2025

  With the rise of AI-generated content (AIGC), generating perceptually natural and feeling-aligned music from multimodal inputs has become a central challenge. Existing approaches often rely on explicit emotion labels that require costly annotation, underscoring the need for more flexible feeling-ali…

• Consistency Flow Model Achieves One-step Denoising Error Correction Codes

  Haoyu Lei, Chin Wa Lau, Kaiwen Zhou, Nian Guo, Farzan Farnia · 2. Dezember 2025

  Error Correction Codes (ECC) are fundamental to reliable digital communication, yet designing neural decoders that are both accurate and computationally efficient remains challenging. Recent denoising diffusion decoders with transformer backbones achieve state-of-the-art performance, but their itera…

• A Sampling-Based Domain Generalization Study with Diffusion Generative Models

  Ye Zhu, Yu Wu, Duo Xu, Zhiwei Deng, Yan Yan, Olga Russakovsky · 1. Dezember 2025

  In this work, we investigate the domain generalization capabilities of diffusion models in the context of synthesizing images that are distinct from the training data. Instead of fine-tuning, we tackle this challenge from a sampling-based perspective using frozen, pre-trained diffusion models. Speci…

• Geometric Regularity in Deterministic Sampling of Diffusion-based Generative Models

  Defang Chen, Zhenyu Zhou, Can Wang, Siwei Lyu · 1. Dezember 2025

  Diffusion-based generative models employ stochastic differential equations (SDEs) and their equivalent probability flow ordinary differential equations (ODEs) to establish a smooth transformation between complex high-dimensional data distributions and tractable prior distributions. In this paper, we…

• Beyond Scores: Proximal Diffusion Models

  Zhenghan Fang, Mateo D\'iaz, Sam Buchanan, Jeremias Sulam · 1. Dezember 2025

  Diffusion models have quickly become some of the most popular and powerful generative models for high-dimensional data. The key insight that enabled their development was the realization that access to the score -- the gradient of the log-density at different noise levels -- allows for sampling from…

• Composition and Alignment of Diffusion Models using Constrained Learning

  Shervin Khalafi, Ignacio Hounie, Dongsheng Ding, Alejandro Ribeiro · 1. Dezember 2025

  Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions. To improve the quality of generated samples and their compliance with user requirements, two commonly used methods are: (i) Alignment, which involves finetuning a diffusion model …

• Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models

  H\'ector Laria, Alexandra Gomez-Villa, Jiang Qin, Muhammad Atif Butt, Bogdan Raducanu, Javier Vazquez-Corral, Joost van de Weijer, Kai Wang · 1. Dezember 2025

  Recent advances in text-to-image (T2I) diffusion models have enabled remarkable control over various attributes, yet precise color specification remains a fundamental challenge. Existing approaches, such as ColorPeel, rely on model personalization, requiring additional optimization and limiting flex…