Generative Adversarial Networks and Image Synthesis

Latest papers

• Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation

  Minyoung Kim · 23 March 2026

  Current auto-regressive (AR) LLMs, diffusion-based text/image generative models, and recent flow matching (FM) algorithms are capable of generating premium quality text/image samples. However, the inference or sample generation in these models is often very time-consuming and computationally demandi…

• Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture -- Bridging Predictive and Generative Self-Supervised Learning

  Moritz G\"ogl, Christopher Yau · 23 March 2026

  The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizing prediction in representation space rather than reconstruction in observation space. We argue that the resulting separation from probabilistic gen…

• 3D-Consistent Multi-View Editing by Correspondence Guidance

  Josef Bengtson, David Nilsson, Dong In Lee, Yaroslava Lochman, Fredrik Kahl · 23 March 2026

  Recent advancements in diffusion and flow models have greatly improved text-based image editing, yet methods that edit images independently often produce geometrically and photometrically inconsistent results across different views of the same scene. Such inconsistencies are particularly problematic…

• TuLaBM: Tumor-Biased Latent Bridge Matching for Contrast-Enhanced MRI Synthesis

  Atharva Rege, Adinath Madhavrao Dukre, Numan Balci, Dwarikanath Mahapatra, Imran Razzak · 23 March 2026

  Contrast-enhanced magnetic resonance imaging (CE-MRI) plays a crucial role in brain tumor assessment; however, its acquisition requires gadolinium-based contrast agents (GBCAs), which increase costs and raise safety concerns. Consequently, synthesizing CE-MRI from non-contrast MRI (NC-MRI) has emerg…

• OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework

  Weixuan Zeng, Pengcheng Wei, Huaiqing Wang, Boheng Zhang, Jia Sun, Dewen Fan, Lin HE, Long Chen, Qianqian Gan, Fan Yang, Tingting Gao · 23 March 2026

  Despite the rapid advancement of Virtual Try-On (VTON) and Try-Off (VTOFF) technologies, existing VTON methods face challenges with fine-grained detail preservation, generalization to complex scenes, complicated pipeline, and efficient inference. To tackle these problems, we propose OmniDiT, an omni…

• X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving

  Chaoda Zheng, Sean Li, Jinhao Deng, Zhennan Wang, Shijia Chen, Liqiang Xiao, Ziheng Chi, Hongbin Lin, Kangjie Chen, Boyang Wang, Yu Zhang, Xianming Liu · 23 March 2026

  Scalable and reliable evaluation is increasingly critical in the end-to-end era of autonomous driving, where vision--language--action (VLA) policies directly map raw sensor streams to driving actions. Yet, current evaluation pipelines still rely heavily on real-world road testing, which is costly, b…

• ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models

  Mohammad Shahab Sepehri, Asal Mehradfar, Berk Tinaz, Salman Avestimehr, Mahdi Soltanolkotabi · 23 March 2026

  Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To address this limitation, we introduce ATHENA, a model-agnostic, test-time adaptive steering framework that improves object cou…

• LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

  Jiazheng Xing, Fei Du, Hangjie Yuan, Pengwei Liu, Hongbin Xu, Hai Ci, Ruigang Niu, Weihua Chen, Fan Wang, Yong Liu · 23 March 2026

  Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and background elements. However, precise face-attribute alignment across subjects remains challenging, as existing methods …

• R&D: Balancing Reliability and Diversity in Synthetic Data Augmentation for Semantic Segmentation

  Huy Che, Dinh-Duy Phan, Duc-Khai Lam · 20 March 2026

  Collecting and annotating datasets for pixel-level semantic segmentation tasks are highly labor-intensive. Data augmentation provides a viable solution by enhancing model generalization without additional real-world data collection. Traditional augmentation techniques, such as translation, scaling, …

• Latent Causal Modeling for 3D Brain MRI Counterfactuals

  Wei Peng, Tian Xia, Fabio De Sousa Ribeiro, Tomas Bosschieter, Ehsan Adeli, Qingyu Zhao, Ben Glocker, Kilian M. Pohl · 20 March 2026

  The number of samples in structural brain MRI studies is often too small to properly train deep learning models. Generative models show promise in addressing this issue by effectively learning the data distribution and generating high-fidelity MRI. However, they struggle to produce diverse, high-qua…

• Ontology-Guided Diffusion for Zero-Shot Visual Sim2Real Transfer

  Mohamed Youssef, Mayar Elfares, Anna-Maria Meer, Matteo Bortoletto, Andreas Bulling · 20 March 2026

  Bridging the simulation-to-reality (sim2real) gap remains challenging as labelled real-world data is scarce. Existing diffusion-based approaches rely on unstructured prompts or statistical alignment, which do not capture the structured factors that make images look real. We introduce Ontology- Guide…

• SRRM: Improving Recursive Transport Surrogates in the Small-Discrepancy Regime

  Yufei Zhang, Tao Wang, Jingyi Zhang · 20 March 2026

  Recursive partitioning methods provide computationally efficient surrogates for the Wasserstein distance, yet their statistical behavior and their resolution in the small-discrepancy regime remain insufficiently understood. We study Recursive Rank Matching (RRM) as a representative instance of this …

• Spectrally-Guided Diffusion Noise Schedules

  Carlos Esteves, Ameesh Makadia · 20 March 2026

  Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels traversed during sampling. Noise schedules are typically handcr…

• Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression

  Minjun Kim, Jaehyeon Choi, Hyunwoo Yang, Jongjin Kim, Jinho Song, U Kang · 20 March 2026

  What happens when multiple compression methods are combined-does the order in which they are applied matter? Joint model compression has emerged as a powerful strategy to achieve higher efficiency by combining multiple methods such as pruning and quantization. A central but underexplored factor in j…

• CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

  Weilin Chen, Jiahao Rao, Wenhao Wang, Xinyang Li, Xuan Cheng, Liujuan Cao · 20 March 2026

  The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures with insufficient quality, artifacts, and baked-in shading. …

• The Exponentially Weighted Signature

  Alexandre Bloch, Samuel N. Cohen, Terry Lyons, Jo\"el Mouterde, Benjamin Walker · 20 March 2026

  The signature is a canonical representation of a multidimensional path over an interval. However, it treats all historical information uniformly, offering no intrinsic mechanism for contextualising the relevance of the past. To address this, we introduce the Exponentially Weighted Signature (EWS), g…

• Translating MRI to PET through Conditional Diffusion Models with Enhanced Pathology Awareness

  Yitong Li, Igor Yakushev, Dennis M. Hedderich, Christian Wachinger · 20 March 2026

  Positron emission tomography (PET) is a widely recognized technique for diagnosing neurodegenerative diseases, offering critical functional insights. However, its high costs and radiation exposure hinder its widespread use. In contrast, magnetic resonance imaging (MRI) does not involve such limitati…

• Seasoning Generative Models for a Generalization Aftertaste

  Hisham Husain, Valentin De Bortoli, Richard Nock · 20 March 2026

  The use of discriminators to train or fine-tune generative models has proven to be a rather successful framework. A notable example is Generative Adversarial Networks (GANs) that minimize a loss incurred by training discriminators along with other paradigms that boost generative models via discrimin…

• Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling

  Sooyoung Ryu, Mathieu Salzmann, Saqib Javed · 20 March 2026

  Post-training quantization (PTQ) is a practical path to deploy large diffusion models, but quantization noise can accumulate over the denoising trajectory and degrade generation quality. We propose Q-Drift, a principled sampler-side correction that treats quantization error as an implicit stochastic…

• Epistemic Generative Adversarial Networks

  Muhammad Mubashar, Fabio Cuzzolin · 20 March 2026

  Generative models, particularly Generative Adversarial Networks (GANs), often suffer from a lack of output diversity, frequently generating similar samples rather than a wide range of variations. This paper introduces a novel generalization of the GAN loss function based on Dempster-Shafer theory of…

• DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding

  Dong Zhuo, Wenzhao Zheng, Sicheng Zuo, Siming Yan, Lu Hou, Jie Zhou, Jiwen Lu · 20 March 2026

  With the growing adoption of vision-language-action models and world models in autonomous driving systems, scalable image tokenization becomes crucial as the interface for the visual modality. However, most existing tokenizers are designed for monocular and 2D scenes, leading to inefficiency and int…

• Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation

  Xuwang Yin, Claire Zhang, Julie Steele, Nir Shavit, Tony T. Wang · 19 March 2026

  Simultaneously achieving robust classification and high-fidelity generative modeling within a single framework presents a significant challenge. Hybrid approaches, such as Joint Energy-Based Models (JEM), interpret classifiers as EBMs but are often limited by the instability and poor sample quality …

• ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation

  Dmitriy Rivkin, Parker Ewen, Lili Gao, Julian Ost, Stefanie Walz, Rasika Kangutkar, Mario Bijelic, Felix Heide · 19 March 2026

  Recent video diffusion models achieve high-quality generation through recurrent frame processing where each frame generation depends on previous frames. However, this recurrent mechanism means that training such models in the pixel domain incurs prohibitive memory costs, as activations accumulate ac…

• Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models

  Jaemin Kim, Jong Chul Ye · 19 March 2026

  Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge, it introduces retrieval-prior conflicts that can degrade ge…

• Arch-VQ: Discrete Architecture Representation Learning with Autoregressive Priors

  Deshani Geethika Poddenige, Sachith Seneviratne, Asela Hevapathige, Damith Senanayake, Mahesan Niranjan, PN Suganthan, Saman Halgamuge · 19 March 2026

  Existing neural architecture representation learning methods focus on continuous representation learning, typically using Variational Autoencoders (VAEs) to map discrete architectures onto a continuous Gaussian distribution. However, sampling from these spaces often leads to a high percentage of inv…