Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation

  Chuancheng Shi, Shangze Li, Shiming Guo, Simiao Xie, Wenhua Wu, Jingtong Dou, Chao Wu, Canran Xiao, Cong Wang, Zifeng Cheng, Fei Shen, Tat-Seng Chua · 24. November 2025

  Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilized. Yet outputs vary across cultural contexts: because language carries cultural connotations, images synthesized from multilingual prompts should preserve cross-…

• CharCom: Composable Identity Control for Multi-Character Story Illustration

  Zhongsheng Wang, Ming Lin, Zhedong Lin, Yaser Shakib, Qian Liu, Jiamou Liu · 24. November 2025

  Ensuring character identity consistency across varying prompts remains a fundamental limitation in diffusion-based text-to-image generation. We propose CharCom, a modular and parameter-efficient framework that achieves character-consistent story illustration through composable LoRA adapters, enablin…

• PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation

  Ting Pan, Ye Wang, Peiguang Jing, Rui Ma, Zili Yi, Yu Liu · 24. November 2025

  Personalized dual-person portrait customization has considerable potential applications, such as preserving emotional memories and facilitating wedding photography planning. However, the absence of a benchmark dataset hinders the pursuit of high-quality customization in dual-person portrait generati…

• Spanning Tree Autoregressive Visual Generation

  Sangkyu Lee, Changho Lee, Janghoon Han, Hosung Song, Tackgeun You, Hwasup Lim, Stanley Jungkyu Choi, Honglak Lee, Youngjae Yu · 24. November 2025

  We present Spanning Tree Autoregressive (STAR) modeling, which can incorporate prior knowledge of images, such as center bias and locality, to maintain sampling performance while also providing sufficiently flexible sequence orders to accommodate image editing at inference. Approaches that expose ra…

• Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder

  Chao Wu, Zhenyi Wang, Kangxian Xie, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Mingchen Gao · 24. November 2025

  Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents SAE Debias, a lightweight and model-agnostic framework for mitigating such bias in T2I generation. Unlike prior approac…

• Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representational Alignment

  Loukas Sfountouris, Giannis Daras, Paris Giampouras · 24. November 2025

  Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to provide a powerful inductive bias, improving both convergence and sample quality. In this work, we extend this idea to inv…

• Real-Time Cooked Food Image Synthesis and Visual Cooking Progress Monitoring on Edge Devices

  Jigyasa Gupta, Soumya Goyal, Anil Kumar, Ishan Jindal · 24. November 2025

  Synthesizing realistic cooked food images from raw inputs on edge devices is a challenging generative task, requiring models to capture complex changes in texture, color and structure during cooking. Existing image-to-image generation methods often produce unrealistic results or are too resource-int…

• ReBaPL: Repulsive Bayesian Prompt Learning

  Yassir Bendou, Omar Ezzahir, Eduardo Fernandes Montesuma, Gabriel Mahuas, Victoria Shevchenko, Mike Gartrell · 24. November 2025

  Prompt learning has emerged as an effective technique for fine-tuning large-scale foundation models for downstream tasks. However, conventional prompt tuning methods are prone to overfitting and can struggle with out-of-distribution generalization. To address these limitations, Bayesian prompt learn…

• Breaking the Bottleneck with DiffuApriel: High-Throughput Diffusion LMs with Mamba Backbone

  Vaibhav Singh, Oleksiy Ostapenko, Pierre-Andr\'e No\"el, Torsten Scholak · 21. November 2025

  Diffusion-based language models have recently emerged as a promising alternative to autoregressive generation, yet their reliance on Transformer backbones limits inference efficiency due to quadratic attention and KV-cache overhead. In this work, we introduce DiffuApriel, a masked diffusion language…

• gfnx: Fast and Scalable Library for Generative Flow Networks in JAX

  Daniil Tiapkin, Artem Agarkov, Nikita Morozov, Ian Maksimov, Askar Tsyganov, Timofei Gritsaev, Sergey Samsonov · 21. November 2025

  In this paper, we present gfnx, a fast and scalable package for training and evaluating Generative Flow Networks (GFlowNets) written in JAX. gfnx provides an extensive set of environments and metrics for benchmarking, accompanied with single-file implementations of core objectives for training GFlow…

• Latent space analysis and generalization to out-of-distribution data

  Katie Rainey, Erin Hausmann, Donald Waagen, David Gray, Donald Hulsey · 20. November 2025

  Understanding the relationships between data points in the latent decision space derived by the deep learning system is critical to evaluating and interpreting the performance of the system on real world data. Detecting \textit{out-of-distribution} (OOD) data for deep learning systems continues to b…

• D4C: Data-free Quantization for Contrastive Language-Image Pre-training Models

  Wenlun Zhang, Yunshan Zhong, Zihao Ding, Xinyu Li, Kentaro Yoshioka · 20. November 2025

  Data-Free Quantization (DFQ) offers a practical solution for model compression without requiring access to real data, making it particularly attractive in privacy-sensitive scenarios. While DFQ has shown promise for unimodal models, its extension to Vision-Language Models such as Contrastive Languag…

• DCL-SE: Dynamic Curriculum Learning for Spatiotemporal Encoding of Brain Imaging

  Meihua Zhou, Xinyu Tong, Jiarui Zhao, Min Cheng, Li Yang, Lei Tian, Nan Wan · 20. November 2025

  High-dimensional neuroimaging analyses for clinical diagnosis are often constrained by compromises in spatiotemporal fidelity and by the limited adaptability of large-scale, general-purpose models. To address these challenges, we introduce Dynamic Curriculum Learning for Spatiotemporal Encoding (DCL…

• Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

  Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko, Denis Parkhomenko, Viacheslav Vasilev, Alexey Letunovskiy, Maria Kovaleva, Nikolai Vaulin, Ivan Kirillov, Lev Novitskiy, Denis Koposov, Nikita Kiselev, Alexander Varlamov, Dmitrii Mikhailov, Vladimir Polovnikov, Andrey Shutkin, Ilya Vasiliev, Julia Agafonova, Anastasiia Kargapoltseva, Anna Dmitrienko, Anastasia Maltseva, Anna Averchenkova, Olga Kim, Tatiana Nikulina, Denis Dimitrov · 20. November 2025

  This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core line-up of models: Kandinsky 5.0 Image Lite - a line-up of 6B parameter image generation models, Kandinsky 5.0 Video Lite -…

• Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning

  Yuxuan Gu, Weimin Bai, Yifei Wang, Weijian Luo, He Sun · 20. November 2025

  Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vanilla MAR suffers from slow inference due to its hierarchical inference mechanism: an outer AR unmasking loop and an inner…

• Walrus: A Cross-Domain Foundation Model for Continuum Dynamics

  Michael McCabe, Payel Mukhopadhyay, Tanya Marwah, Bruno Regaldo-Saint Blancard, Francois Rozet, Cristiana Diaconu, Lucas Meyer, Kaze W. K. Wong, Hadi Sotoudeh, Alberto Bietti, Irina Espejo, Rio Fear, Siavash Golkar, Tom Hehir, Keiya Hirashima, Geraud Krawezik, Francois Lanusse, Rudy Morel, Ruben Ohana, Liam Parker, Mariel Pettee, Jeff Shen, Kyunghyun Cho, Miles Cranmer, Shirley Ho · 20. November 2025

  Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unstable long-term dynamics inhibit learning from sufficiently diverse dynamics, while varying resolutions and dimensionalit…

• SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

  Jintao Zhang, Haoxu Wang, Kai Jiang, Shuo Yang, Kaiwen Zheng, Haocheng Xi, Ziteng Wang, Hongzhou Zhu, Min Zhao, Ion Stoica, Joseph E. Gonzalez, Jun Zhu, Jianfei Chen · 20. November 2025

  In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts: a small fraction of large weights with high rank and the rem…

• Nonparametric estimation of conditional probability distributions using a generative approach based on conditional push-forward neural networks

  Nicola Rares Franco, Lorenzo Tedesco · 19. November 2025

  We introduce conditional push-forward neural networks (CPFN), a generative framework for conditional distribution estimation. Instead of directly modeling the conditional density $f_{Y|X}$, CPFN learns a stochastic map $\varphi=\varphi(x,u)$ such that $\varphi(x,U)$ and $Y|X=x$ follow approximately …

• A Disentangled Low-Rank RNN Framework for Uncovering Neural Connectivity and Dynamics

  Chengrui Li, Yunmiao Wang, Yule Wang, Weihan Li, Dieter Jaeger, Anqi Wu · 19. November 2025

  Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks disentanglement interpretations, making it difficult to assign distinct computational rol…

• Training-free Detection of AI-generated images via Cropping Robustness

  Sungik Choi, Hankook Lee, Moontae Lee · 19. November 2025

  AI-generated image detection has become crucial with the rapid advancement of vision-generative models. Instead of training detectors tailored to specific datasets, we study a training-free approach leveraging self-supervised models without requiring prior data knowledge. These models, pre-trained w…

• Splat Regression Models

  Mara Daniels, Philippe Rigollet · 19. November 2025

  We introduce a highly expressive class of function approximators called Splat Regression Models. Model outputs are mixtures of heterogeneous and anisotropic bump functions, termed splats, each weighted by an output vector. The power of splat modeling lies in its ability to locally adjust the scale a…

• DeCo-VAE: Learning Compact Latents for Video Reconstruction via Decoupled Representation

  Xiangchen Yin, Jiahui Yuan, Zhangchi Hu, Wenzhang Sun, Jie Chen, Xiaozhen Qiao, Hao Li, Xiaoyan Sun · 19. November 2025

  Existing video Variational Autoencoders (VAEs) generally overlook the similarity between frame contents, leading to redundant latent modeling. In this paper, we propose decoupled VAE (DeCo-VAE) to achieve compact latent representation. Instead of encoding RGB pixels directly, we decompose video cont…

• ForensicFlow: A Tri-Modal Adaptive Network for Robust Deepfake Detection

  Mohammad Romani · 19. November 2025

  Deepfakes generated by advanced GANs and autoencoders severely threaten information integrity and societal stability. Single-stream CNNs fail to capture multi-scale forgery artifacts across spatial, texture, and frequency domains, limiting robustness and generalization. We introduce the ForensicFlow…

• ODE$_t$(ODE$_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling

  Denis Gudovskiy, Wenzhao Zheng, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer · 19. November 2025

  Continuous normalizing flows (CNFs) and diffusion models (DMs) generate high-quality data from a noise distribution. However, their sampling process demands multiple iterations to solve an ordinary differential equation (ODE) with high computational complexity. State-of-the-art methods focus on redu…

• Personalized Image Generation for Recommendations Beyond Catalogs

  Gabriel Patron, Zhiwei Xu, Ishan Kapnadak, Felipe Maia Polo · 19. November 2025

  Personalization is central to human-AI interaction, yet current diffusion-based image generation systems remain largely insensitive to user diversity. Existing attempts to address this often rely on costly paired preference data or introduce latency through Large Language Models. In this work, we in…