Generative Adversarial Networks and Image Synthesis

Últimos artículos

• ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor

  Yixiao Wang, Ting Jiang, Zishan Shao, Hancheng Ye, Jingwei Sun, Mingyuan Ma, Jianyi Zhang, Yiran Chen, Hai Li · 3 de abril de 2026

  Denoising generative models deliver high-fidelity generation but remain bottlenecked by inference latency due to the many iterative denoiser calls required during sampling. Training-free acceleration methods reduce latency by either sparsifying the model architecture or shortening the sampling traje…

• JetPrism: diagnosing convergence for generative simulation and inverse problems in nuclear physics

  Zeyu Xia, Tyler Kim, Trevor Reed, Judy Fox, Geoffrey Fox, Adam Szczepaniak · 3 de abril de 2026

  High-fidelity Monte Carlo simulations and complex inverse problems, such as mapping smeared experimental observations to ground-truth states, are computationally intensive yet essential for robust data analysis. Conditional Flow Matching (CFM) offers a mathematically robust approach to accelerating …

• Demystifying Transition Matching: When and Why It Can Beat Flow Matching

  Jaihoon Kim, Rajarshi Saha, Minhyuk Sung, Youngsuk Park · 3 de abril de 2026

  Flow Matching (FM) underpins many state-of-the-art generative models, yet recent results indicate that Transition Matching (TM) can achieve higher quality with fewer sampling steps. This work answers the question of when and why TM outperforms FM. First, when the target is a unimodal Gaussian distri…

• Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images

  Jamie S. J. Stirling, Noura Al-Moubayed, Hubert P. H. Shum · 3 de abril de 2026

  Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive or diffusion-based priors to model their dependencies at sam…

• SYNTHONY: A Stress-Aware, Intent-Conditioned Agent for Deep Tabular Generative Models Selection

  Hochan Son, Xiaofeng Lin, Jason Ni, Guang Cheng · 2 de abril de 2026

  Deep generative models for tabular data (GANs, diffusion models, and LLM-based generators) exhibit highly non-uniform behavior across datasets; the best-performing synthesizer family depends strongly on distributional stressors such as long-tailed marginals, high-cardinality categorical, Zipfian imb…

• Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment

  Kai Nelson, Tobias Kreiman, Sergey Levine, Aditi S. Krishnapriyan · 2 de abril de 2026

  A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too difficult to solve exactly for complex systems. Such systems are commonly modeled using simulators, which impose computation…

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

  Wenlun Zhang, Yunshan Zhong, Zihao Ding, Xinyu Li, Kentaro Yoshioka · 2 de abril de 2026

  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…

• Deep Networks Favor Simple Data

  Weyl Lu, Chenjie Hao, Yubei Chen · 2 de abril de 2026

  Estimated density is often interpreted as indicating how typical a sample is under a model. Yet deep models trained on one dataset can assign \emph{higher} density to simpler out-of-distribution (OOD) data than to in-distribution test data. We refer to this behavior as the OOD anomaly. Prior work ty…

• Brain MR Image Synthesis with Multi-contrast Self-attention GAN

  Zaid A. Abod, Furqan Aziz · 2 de abril de 2026

  Accurate and complete multi-modal Magnetic Resonance Imaging (MRI) is essential for neuro-oncological assessment, as each contrast provides complementary anatomical and pathological information. However, acquiring all modalities (e.g., T1c, T1n, T2, T2f) for every patient is often impractical due to…

• TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models

  Awais Khan, Muhammad Umar Farooq, Kutub Uddin, Khalid Malik · 2 de abril de 2026

  Partial audio deepfakes, where synthesized segments are spliced into genuine recordings, are particularly deceptive because most of the audio remains authentic. Existing detectors are supervised: they require frame-level annotations, overfit to specific synthesis pipelines, and must be retrained as …

• Science-T2I: Addressing Scientific Illusions in Image Synthesis

  Jialuo Li, Wenhao Chai, Xingyu Fu, Haiyang Xu, Saining Xie · 2 de abril de 2026

  Current image generation models produce visually compelling but scientifically implausible images, exposing a fundamental gap between visual fidelity and physical realism. In this work, we introduce ScienceT2I, an expert-annotated dataset comprising a training set of over 20k adversarial image pairs…

• Disentanglement of Sources in a Multi-Stream Variational Autoencoder

  Veranika Boukun, J\"org L\"ucke · 2 de abril de 2026

  Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent space. In this paper, we propose and provide a proof of concept…

• MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation

  Bharath Krishnamurthy, Ajita Rattani · 1 de abril de 2026

  Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal fusion enables controllable synthesis aligned with both hig…

• Turbo4DGen: Ultra-Fast Acceleration for 4D Generation

  Yuanbin Man, Ying Huang, Zhile Ren, Miao Yin · 1 de abril de 2026

  4D generation, or dynamic 3D content generation, integrates spatial, temporal, and view dimensions to model realistic dynamic scenes, playing a foundational role in advancing world models and physical AI. However, maintaining long-chain consistency across both frames and viewpoints through the uniqu…

• ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images

  Xianghao Kong, Qiaosong Qi, Yuanbin Wang, Biaolong Chen, Aixi Zhang, Anyi Rao · 1 de abril de 2026

  Fashion video generation aims to synthesize temporally consistent videos from reference images of a designated character. Despite significant progress, existing diffusion-based methods only support a single reference image as input, severely limiting their capability to generate view-consistent fash…

• iPoster: Content-Aware Layout Generation for Interactive Poster Design via Graph-Enhanced Diffusion Models

  Xudong Zhou, Jinyuan Liang, Qiuyi Guo, Guozheng Li · 1 de abril de 2026

  We present iPoster, an interactive layout generation framework that empowers users to guide content-aware poster layout design by specifying flexible constraints. iPoster enables users to specify partial intentions within the intention module, such as element categories, sizes, positions, or coarse …

• MacTok: Robust Continuous Tokenization for Image Generation

  Hengyu Zeng, Xin Gao, Guanghao Li, Yuxiang Yan, Jiaoyang Ruan, Junpeng Ma, Haoyu Albert Wang, Jian Pu · 1 de abril de 2026

  Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularization. Yet this often leads to posterior collapse when using fewer tokens, where the encoder fails to encode informative f…

• $R_\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation

  Linqian Fan, Peiqin Sun, Tiancheng Wen, Shun Lu, Chengru Song · 1 de abril de 2026

  Diffusion models achieve state-of-the-art generative performance but are fundamentally bottlenecked by their slow, iterative sampling process. While diffusion distillation techniques enable high-fidelity, few-step generation, traditional objectives often restrict the student's performance by anchori…

• SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation

  Ryosuke Matsuda, Keito Kudo, Haruto Yoshida, Nobuyuki Shimizu, Jun Suzuki · 1 de abril de 2026

  This paper proposes the synthetic long-video meta-evaluation (SLVMEval), a benchmark for meta-evaluating text-to-video (T2V) evaluation systems. The proposed SLVMEval benchmark focuses on assessing these systems on videos of up to 10,486 s (approximately 3 h). The benchmark targets a fundamental req…

• CIPHER: Counterfeit Image Pattern High-level Examination via Representation

  Kyeonghun Kim, Youngung Han, Seoyoung Ju, Yeonju Jean, YooHyun Kim, Minseo Choi, SuYeon Lim, Kyungtae Park, Seungwoo Baek, Sieun Hyeon, Nam-Joon Kim, Hyuk-Jae Lee · 1 de abril de 2026

  The rapid progress of generative adversarial networks (GANs) and diffusion models has enabled the creation of synthetic faces that are increasingly difficult to distinguish from real images. This progress, however, has also amplified the risks of misinformation, fraud, and identity abuse, underscori…

• Enhancing Policy Learning with World-Action Model

  Yuci Han, Alper Yilmaz · 1 de abril de 2026

  This paper presents the World-Action Model (WAM), an action-regularized world model that jointly reasons over future visual observations and the actions that drive state transitions. Unlike conventional world models trained solely via image prediction, WAM incorporates an inverse dynamics objective …

• The Mouth is Not the Brain: Bridging Energy-Based World Models and Language Generation

  Junichiro Niimi · 1 de abril de 2026

  Large Language Models (LLMs) generate fluent text, yet whether they truly understand the world or merely produce plausible texts about it remains contested. We propose an architectural principle, the mouth is not the brain, that explicitly separates world models from language models. Our architectur…

• DF-ACBlurGAN: Structure-Aware Conditional Generation of Internally Repeated Patterns for Biomaterial Microtopography Design

  Rongjun Dong, Xin Chen, Morgan R Alexander, Karthikeyan Sivakumar, Reza Omdivar, David A Winkler, Grazziela Figueredo · 1 de abril de 2026

  Learning to generate images with internally repeated and periodic structures poses a fundamental challenge for machine learning and computer vision models, which are typically optimised for local texture statistics and semantic realism rather than global structural consistency. This limitation is pa…

• Extend3D: Town-Scale 3D Generation

  Seungwoo Yoon, Jinmo Kim, Jaesik Park · 1 de abril de 2026

  In this paper, we propose Extend3D, a training-free pipeline for 3D scene generation from a single image, built upon an object-centric 3D generative model. To overcome the limitations of fixed-size latent spaces in object-centric models for representing wide scenes, we extend the latent space in the…

• Image-Adaptive GAN based Reconstruction

  Shady Abu Hussein, Tom Tirer, Raja Giryes · 31 de marzo de 2026

  In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of these methods still do not capture the full distribution for…