Generative Adversarial Networks and Image Synthesis

Últimos artículos

• Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

  Zhe Huang, Hao Wen, Aiming Hao, Bingze Song, Meiqi Wu, Jiahong Wu, Xiangxiang Chu, Sheng Lu, Haoqian Wang · 1 de enero de 2026

  Multimodal Large Language Models (MLLMs) have made remarkable progress in video understanding. However, they suffer from a critical vulnerability: an over-reliance on language priors, which can lead to visual ungrounded hallucinations, especially when processing counterfactual videos that defy commo…

• HaineiFRDM: Explore Diffusion to Restore Defects in Fast-Movement Films

  Rongji Xun, Junjie Yuan, Zhongjie Wang · 1 de enero de 2026

  Existing open-source film restoration methods show limited performance compared to commercial methods due to training with low-quality synthetic data and employing noisy optical flows. In addition, high-resolution films have not been explored by the open-source methods.We propose HaineiFRDM(Film Res…

• Implicit geometric regularization in flow matching via density weighted Stein operators

  Shinto Eguchi · 1 de enero de 2026

  Flow Matching (FM) has emerged as a powerful paradigm for continuous normalizing flows, yet standard FM implicitly performs an unweighted $L^2$ regression over the entire ambient space. In high dimensions, this leads to a fundamental inefficiency: the vast majority of the integration domain consists…

• Attribution-Guided Distillation of Matryoshka Sparse Autoencoders

  Cristina P. Martin-Linares, Jonathan P. Ling · 1 de enero de 2026

  Sparse autoencoders (SAEs) aim to disentangle model activations into monosemantic, human-interpretable features. In practice, learned features are often redundant and vary across training runs and sparsity levels, which makes interpretations difficult to transfer and reuse. We introduce Distilled Ma…

• An Adaptive, Disentangled Representation for Multidimensional MRI Reconstruction

  Ruiyang Zhao, Fan Lam · 1 de enero de 2026

  We present a new approach for representing and reconstructing multidimensional magnetic resonance imaging (MRI) data. Our method builds on a novel, learned feature-based image representation that disentangles different types of features, such as geometry and contrast, into distinct low-dimensional l…

• SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time

  Zhening Huang, Hyeonho Jeong, Xuelin Chen, Yulia Gryaditskaya, Tuanfeng Y. Wang, Joan Lasenby, Chun-Hao Huang · 1 de enero de 2026

  We present SpaceTimePilot, a video diffusion model that disentangles space and time for controllable generative rendering. Given a monocular video, SpaceTimePilot can independently alter the camera viewpoint and the motion sequence within the generative process, re-rendering the scene for continuous…

• Gradient Descent as Implicit EM in Distance-Based Neural Models

  Alan Oursland · 1 de enero de 2026

  Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in attention mechanisms, classification heads, and energy-based m…

• Generative Classifiers Avoid Shortcut Solutions

  Alexander C. Li, Ananya Kumar, Deepak Pathak · 1 de enero de 2026

  Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the label. We show that generative classifiers, which use class-condi…

• Guiding a Diffusion Transformer with the Internal Dynamics of Itself

  Xingyu Zhou, Qifan Li, Xiaobin Hu, Hai Chen, Shuhang Gu · 1 de enero de 2026

  The diffusion model presents a powerful ability to capture the entire (conditional) data distribution. However, due to the lack of sufficient training and data to learn to cover low-probability areas, the model will be penalized for failing to generate high-quality images corresponding to these area…

• Flow Matching Neural Processes

  Hussen Abu Hamad, Dan Rosenbaum · 1 de enero de 2026

  Neural processes (NPs) are a class of models that learn stochastic processes directly from data and can be used for inference, sampling and conditional sampling. We introduce a new NP model based on flow matching, a generative modeling paradigm that has demonstrated strong performance on various dat…

• Quantum Generative Models for Computational Fluid Dynamics: A First Exploration of Latent Space Learning in Lattice Boltzmann Simulations

  Achraf Hsain, Fouad Mohammed Abbou · 30 de diciembre de 2025

  This paper presents the first application of quantum generative models to learned latent space representations of computational fluid dynamics (CFD) data. While recent work has explored quantum models for learning statistical properties of fluid systems, the combination of discrete latent space comp…

• JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference

  Niels Bracher, Lars K\"uhmichel, Desi R. Ivanova, Xavier Intes, Paul-Christian B\"urkner, Stefan T. Radev · 30 de diciembre de 2025

  We consider problems of parameter estimation where design variables can be actively optimized to maximize information gain. To this end, we introduce JADAI, a framework that jointly amortizes Bayesian adaptive design and inference by training a policy, a history network, and an inference network end…

• Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Information

  Youngchae Kwon, Jinyoung Choi, Injung Kim · 30 de diciembre de 2025

  Fashion item detection is challenging due to the ambiguities introduced by the highly diverse appearances of fashion items and the similarities among item subcategories. To address this challenge, we propose a novel Holistic Detection Transformer (Holi-DETR) that detects fashion items in outfit imag…

• Seeing Isn't Believing: Context-Aware Adversarial Patch Synthesis via Conditional GAN

  Roie Kazoom, Alon Goldberg, Hodaya Cohen, Ofer Hadar · 30 de diciembre de 2025

  Adversarial patch attacks pose a severe threat to deep neural networks, yet most existing approaches rely on unrealistic white-box assumptions, untargeted objectives, or produce visually conspicuous patches that limit real-world applicability. In this work, we introduce a novel framework for fully c…

• CoFi-Dec: Hallucination-Resistant Decoding via Coarse-to-Fine Generative Feedback in Large Vision-Language Models

  Zongsheng Cao, Yangfan He, Anran Liu, Jun Xie, Feng Chen, Zepeng Wang · 30 de diciembre de 2025

  Large Vision-Language Models (LVLMs) have achieved impressive progress in multi-modal understanding and generation. However, they still tend to produce hallucinated content that is inconsistent with the visual input, which limits their reliability in real-world applications. We propose \textbf{CoFi-…

• Stochastic Siamese MAE Pretraining for Longitudinal Medical Images

  Taha Emre, Arunava Chakravarty, Thomas Pinetz, Dmitrii Lachinov, Martin J. Menten, Hendrik Scholl, Sobha Sivaprasad, Daniel Rueckert, Andrew Lotery, Stefan Sacu, Ursula Schmidt-Erfurth, Hrvoje Bogunovi\'c · 30 de diciembre de 2025

  Temporally aware image representations are crucial for capturing disease progression in 3D volumes of longitudinal medical datasets. However, recent state-of-the-art self-supervised learning approaches like Masked Autoencoding (MAE), despite their strong representation learning capabilities, lack te…

• PathoSyn: Imaging-Pathology MRI Synthesis via Disentangled Deviation Diffusion

  Jian Wang, Sixing Rong, Jiarui Xing, Yuling Xu, Weide Liu · 30 de diciembre de 2025

  We present PathoSyn, a unified generative framework for Magnetic Resonance Imaging (MRI) image synthesis that reformulates imaging-pathology as a disentangled additive deviation on a stable anatomical manifold. Current generative models typically operate in the global pixel domain or rely on binary …

• Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model

  Renping Zhou, Zanlin Ni, Tianyi Chen, Zeyu Liu, Yang Yue, Yulin Wang, Yuxuan Wang, Jingshu Liu, Gao Huang · 30 de diciembre de 2025

  Recently, Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation. However, a notable discrepancy exists between their training and inference procedures. In particular, MDM inference is a multi-step, iterative process governed not only by the…

• Self-Evaluation Unlocks Any-Step Text-to-Image Generation

  Xin Yu, Xiaojuan Qi, Zhengqi Li, Kai Zhang, Richard Zhang, Zhe Lin, Eli Shechtman, Tianyu Wang, Yotam Nitzan · 30 de diciembre de 2025

  We introduce the Self-Evaluating Model (Self-E), a novel, from-scratch training approach for text-to-image generation that supports any-step inference. Self-E learns from data similarly to a Flow Matching model, while simultaneously employing a novel self-evaluation mechanism: it evaluates its own g…

• Characterizing Motion Encoding in Video Diffusion Timesteps

  Vatsal Baherwani, Yixuan Ren, Abhinav Shrivastava · 30 de diciembre de 2025

  Text-to-video diffusion models synthesize temporal motion and spatial appearance through iterative denoising, yet how motion is encoded across timesteps remains poorly understood. Practitioners often exploit the empirical heuristic that early timesteps mainly shape motion and layout while later ones…

• Decomposing Task Vectors for Refined Model Editing

  Hamed Damirchi, Ehsan Abbasnejad, Zhen Zhang, Javen Shi · 30 de diciembre de 2025

  Large pre-trained models have transformed machine learning, yet adapting these models effectively to exhibit precise, concept-specific behaviors remains a significant challenge. Task vectors, defined as the difference between fine-tuned and pre-trained model parameters, provide a mechanism for steer…

• SpotEdit: Selective Region Editing in Diffusion Transformers

  Zhibin Qin, Zhenxiong Tan, Zeqing Wang, Songhua Liu, Xinchao Wang · 30 de diciembre de 2025

  Diffusion Transformer models have significantly advanced image editing by encoding conditional images and integrating them into transformer layers. However, most edits involve modifying only small regions, while current methods uniformly process and denoise all tokens at every timestep, causing redu…

• AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization

  Binhe Yu, Zhen Wang, Kexin Li, Yuqian Yuan, Wenqiao Zhang, Long Chen, Juncheng Li, Jun Xiao, Yueting Zhuang · 30 de diciembre de 2025

  Multi-subject customization aims to synthesize multiple user-specified subjects into a coherent image. To address issues such as subjects missing or conflicts, recent works incorporate layout guidance to provide explicit spatial constraints. However, existing methods still struggle to balance three …

• Towards Unsupervised Causal Representation Learning via Latent Additive Noise Model Causal Autoencoders

  Hans Jarett J. Ong, Brian Godwin S. Lim, Dominic Dayta, Renzo Roel P. Tan, Kazushi Ikeda · 30 de diciembre de 2025

  Unsupervised representation learning seeks to recover latent generative factors, yet standard methods relying on statistical independence often fail to capture causal dependencies. A central challenge is identifiability: as established in disentangled representation learning and nonlinear ICA litera…

• Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models

  Takuro Kutsuna · 29 de diciembre de 2025

  Diffusion models have become a central tool in deep generative modeling, but standard formulations rely on a single network and a single diffusion schedule to transform a simple prior, typically a standard normal distribution, into the target data distribution. As a result, the model must simultaneo…