Generative Adversarial Networks and Image Synthesis

Derniers papiers

• Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions

  David R. Wessels, Farhad Ramezanghorbani, David W. Romero, Alireza Moradzadeh, Olivia Viessmann, Maksim Zhdanov, John St. John, Ken Janik, David M Knigge, Yucheng Tang, Erik J Bekkers, Saee Gopal Paliwal · 23 juillet 2026

  Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input dependency, while recurrent models require rasterizing data such as images, volumes, and partial differential equation (PDE) into an ad-hoc …

• HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation

  Jinliang Shen, Lianghao Su, Zheming Li, Kang He, ZiLiang Lai, Yanbing Jiang, Chengru Song · 23 juillet 2026

  Autoregressive (AR) video diffusion models have become a promising paradigm for long and streaming video synthesis, but the continuously growing Key-Value (KV) cache makes attention the dominant inference cost, especially at high resolution where each frame contributes many tokens. Existing remedies…

• Enhancing next token prediction based pre-training for jet foundation models

  Joschka Birk, Anna Hallin, Gregor Kasieczka, Nikol Madzharova, Ian Pang, David Shih · 23 juillet 2026

  Next token prediction is an attractive pre-training task for jet foundation models, in that it is simulation free and enables excellent generative capabilities that can transfer across datasets. Here we study multiple improvements to next token prediction, building on the initial work of OmniJet-$\a…

• Bayesian Wind Tunnels for Model Selection

  Siddhartha R Dalal, Vishal Misra, Abhay Parekh · 23 juillet 2026

  Prior work has shown that transformers can perform exact Bayesian filtering within a fixed hypothesis class. Can they also perform Bayesian model selection -- identifying the correct hypothesis class from data? We introduce model-selection Bayesian wind tunnels: controlled environments where g…

• Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparison

  Shijie Zhong, Jiangfeng Fu · 23 juillet 2026

  We introduce the Directional Kernel Mean Difference (DKMD), a signed statistic for univariate distribution comparison that preserves the direction of distributional shifts. Unlike the squared Maximum Mean Discrepancy (MMD), which discards directional information by squaring the RKHS distance, DKMD i…

• Analytic Distribution of Classifier-Free Guidance for Schedule Design

  Enze Jiang, Zheng Ma · 23 juillet 2026

  Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not captured by the usual product-distribution heuristic $p_0^\omega q_0^{1-\omega}$. We analyze CFG through the probability fl…

• AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

  AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao · 22 juillet 2026

  Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly. It enable us to create customized, explorable, and continuously evolving v…

• Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches

  Rick Wilming, Irem Ozseker, Luca Matteo Cornils, Ahc\`ene Boubekki, Benedict Clark, Danny Panknin, Stefan Haufe · 22 juillet 2026

  Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features. However, current approaches rely on expert annotations, which are prone to labeling errors, or on hand-crafted artificial perturbations superimpose…

• One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization

  Haoyue Liu, Xiaoyu Ma, Ye Chen, Shuguang Cui, Xiaoying Tang · 22 juillet 2026

  Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising resu…

• Signed Rectified Flow: Negativity-Controlled Generation

  Runlong Liao, Baiyu Su, Lizhang Chen, Qiang Liu · 22 juillet 2026

  We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $\pi^{sign} = (1+\alpha)\pi^+ - \alpha\pi^-$, where $\alpha>0$, $\pi^+$ is the distribution to promote, and $\pi^-$ is the distribution to suppress. Although direct sampling from a sign…

• Decafs: Disentangled Conditional adversarial Flows

  Anirudh jain, Sakshi Varshney, Samuel Kaski, Vikas Garg · 22 juillet 2026

  Flow-based models have established state-of-the-art performance in generative modeling across domains, but are hard to interpret due to their complex latent embeddings. In particular, the entanglement of generative factors in the latent space hinders controlled generation. We circumvent this issue b…

• FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling

  Jialong Zuo, Haotong Zuo, Shiwei Zhang, Xiang Wang, Chen Li, Nong Sang, Changxin Gao, Xiang Bai · 22 juillet 2026

  Translating novels into films poses a grand challenge for generative artificial intelligence, requiring conversion of abstract literary prose into long-form, multi-scene visual narratives. While current video generation models excel at short, single-scene clips within narrow temporal and spatial con…

• ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

  Chirag Vashist, Ke Li · 22 juillet 2026

  Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and various beliefs about what drives strong empirical performance have taken hold. Due to the success of diffusion models …

• Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

  Xinjie Zhang, Peng Zhang, Shicheng Zheng, Jinghao Guo, Zhaoyang Jia, Yifei Shen, Xun Guo, Yuxuan Luo, Jiahao Li, Wenxuan Xie, Fanyi Pu, Xiaoyi Zhang, Kaichen Zhang, Zongyu Guo, Tianci Bi, Dongnan Gui, Zhening Liu, Zimo Wen, Zihan Zheng, Senqiao Yang, Xiao Li, Jinglu Wang, Bin Li, Yan Lu · 22 juillet 2026

  Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing. The stack is built from two co-designed components: Mage-VAE, a l…

• Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

  Rahul Sajnani, Yulia Gryaditskaya, Radom\'ir M\v{e}ch, Srinath Sridhar, Matheus Gadelha · 22 juillet 2026

  Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements that cannot be reliably achieved through text prompting alone. Diffusion Transformers (DiTs) can natively ingest hetero…

• Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations

  Rong Hu, Ling Chen · 21 juillet 2026

  Disentangled representation learning is a powerful paradigm for robust attribute prediction. While recent methods address attribute correlations, hidden correlations remain underexplored, where data under the value of a certain attribute exhibit underlying modes correlated with other attributes. To …

• Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?

  Aniket Deshpande · 21 juillet 2026

  Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals. We formalize this ambiguity as a matrix-valued distortion between optimal ridge-prediction operators and train decoder-preserving SA…

• Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis

  Minh Tran · 21 juillet 2026

  Neural Radiance Fields (NeRF) have enabled photorealistic novel-view synthesis of 3D scenes and, in the facial domain, have been extended to reconstruct and animate 3D face models from a small number of images. However, existing few-shot dynamic NeRF methods for facial expression editing typically w…

• LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models

  Xingru Chen, Zelang Liang, Yongjia Ma, Jiqing Zhan, Shuling Yang, Lian Wen, Kun Zhan · 21 juillet 2026

  Diffusion-based Large Language Models(DLLMs) enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation. However, current methods suffer from severe operator-level redundancy: they recompute the entire sequence during denoising steps, ignoring that the prefix and masked suf…

• Three-Body Scattering for Generative Modeling

  Peng Sun, Zhenglin Cheng, Deyuan Liu, Jun Xie, Xinyi Shang, Tao Lin · 21 juillet 2026

  Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization. Instead, we show that a proper distributional energy can induce sample-level motion and provide direct regression supervision for a one-step generator. Three-Body Sc…

• Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations

  Changyu Liu, Yuling Jiao, Jian Huang · 21 juillet 2026

  Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant. To effectively leverage structural information embedded within the unlabeled dataset and compensate for sparse conditioning signals, we propose a…

• Semi-Supervised Conditional Diffusion via Label Augmentation

  Jin Su, Yuan Gao, Yong Zhou, Jian Huang · 21 juillet 2026

  Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data. In practice, however, acquiring high-quality labels is costly and time-consuming, leaving large volumes of unlabeled data unused. To address this, we introduce…

• SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift

  Jiaqi Zhu, Xincheng Chen, Yuncheng Wu, Zhaojing Luo, Beng Chin Ooi · 21 juillet 2026

  Generative models trained on a source domain often produce samples that are poorly aligned with shifted target domains, limiting their effectiveness for target-domain data augmentation. Although target-specific adaptation can reduce this mismatch, it typically requires additional optimization and do…

• Learning Spatio-Temporal Foundation Models from Pure Synthetic Data

  Yutong Feng, Shiyuan Piao, Yutong Xia, Xu Liu, Wenqi Fan, Fugee Tsung, See-Kiong Ng, Yuxuan Liang · 21 juillet 2026

  Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time. However, existing approaches suffer from distributional bias in real-world pre-training data, structural bottlenecks of autoregressive or diffusion-based paradigms…

• A${}^2$BM: Alignment-Aware Bridge Matching for Image-to-Image Translation

  Aimi Okabayashi (UBS Vannes), Georges Le Bellier (LIP, CEDRIC - VERTIGO), Nicolas Audebert (LaSTIG, IGN, CEDRIC - VERTIGO), Charlotte Pelletier (OBELIX), Thomas Corpetti (LETG - Rennes), Nicolas Courty (OBELIX) · 21 juillet 2026

  Paired image-to-image translation underpins a wide range of computer vision tasks, including image editing, sensor translation, and domain adaptation. Bridge matching and flow matching have recently emerged as powerful frameworks, extending diffusion models to arbitrary source and target distributio…