Generative Adversarial Networks and Image Synthesis

Derniers papiers

• S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights

  Yi-Shan Chu · 30 juin 2026

  Classical universal approximation theorems establish the expressive power of sigmoidal multilayer perceptrons, but they do not prescribe how initial weights should encode the geometry of a data distribution. We propose S-GAI, a spectral geometry-aware initialization framework for one-hidden-layer si…

• C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

  Haoran Jin, Xiting Wang, Shijie Ren, Hong Xie, Defu Lian · 30 juin 2026

  Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges. Systematic studies reveal pervasive feature splitting that fragments coherent concept…

• Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

  Shihao Zhang, Yuguang Yan, Junzhe Zhang, Wei Zhao, Bohan Wang, Hanwang Zhang · 30 juin 2026

  Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur substantial computational overhead, require costly human annotations, and often yi…

• HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers

  Jing Yang, Mayoore Jaiswal, Zian Wang, Steven Zeng, Rochelle Pereira, Yajie Zhao, Jianyuan Min · 30 juin 2026

  Diffusion-based video relighting enables controllable relighting from a single input video, but modern video diffusion backbones are trained on short clips and applied to long-horizon videos through chunked sliding-window inference, often causing temporal discontinuities at chunk boundaries. We addr…

• Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer

  Francesca Pia Panaccione, Eugenio Lomurno, Francesca Fati, Carlotta Pecchiari, Marina Rosanu, Luigi De Vitis, Lucia Ribero, Gabriella Schivardi, Giovanni Damiano Aletti, Nicoletta Colombo, Maria Francesca Spadea, Francesco Multinu, Matteo Matteucci, Elena De Momi · 30 juin 2026

  Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of generalizable computational m…

• $\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors

  Orazio Pontorno, Mattia Litrico, Luca Guarnera, Mario Valerio Giuffrida, Sebastiano Battiato · 30 juin 2026

  Current generative models, including GANs and diffusion models, have reached an outstanding level of photorealism, posing significant risks to privacy and security. To ensure real-world applicability, deepfake detectors must generalise effectively to unseen generators. However, most existing approac…

• General and Efficient Steering of Diffusion Models

  Qingsong Wang, Mikhail Belkin, Yusu Wang · 30 juin 2026

  Steering diffusion models toward conditions unseen during training typically requires either retraining with conditional inputs or per-step gradient computations, both of which incur substantial computational overhead. We present Noise-Aligned RFM Steering (NA-RFM), a general recipe for efficiently …

• ScaleAware-JEPA: Latent Representation for Discovery in Multiscale Physical Fields

  Guang-Xing Li · 30 juin 2026

  Continuous physical fields represent a large fraction of data under scientific investigation. Their multiscale structures are central to discovery, yet useful coordinates are not known in advance. Standard self-supervised methods define context and targets in fixed image coordinates, posing a predic…

• Simplifying Flow Matching Transformations with Low-Rank Mixture Models

  Liam A. Kruse, Houjun Liu, Alexandros E. Tzikas, Mansur M. Arief, Mykel J. Kochenderfer · 30 juin 2026

  Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal density. However, this choice of latent density can impose unnecessary complexity on the learned flow transformation due t…

• Transformer Architectures as Complete Bayes Processes: A Formal Proof in the Measure-Theoretic Kernel Framework

  Haobo Yang · 30 juin 2026

  We present a complete formal proof that transformer architectures, when their internal update mechanisms satisfy a Bayes joint-distribution condition, implement exact Bayesian posterior inference. Working within the measure-theoretic kernel framework, we define a hierarchy of abstractions -- from th…

• Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps

  RuiKang OuYang, Hanlin Yu, Xinyue Ai, Yutong He, Nicholas M. Boffi, Pradeep Ravikumar, Jose Miguel Hernandez-Lobato, Max Simchowitz, Benjamin Kurt Miller, Omar Chehab · 30 juin 2026

  Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, there is a lack of similar advances in estimating the model likelihood. In particular, most existing methods either rely …

• Perspectives on Latent Factor Indeterminacy and its Implications for Data Representation

  Carel F. W. Peeters · 30 juin 2026

  The common factor analytic model is related to Helmholtz and Boltzmann machines, can be conceived as a linear autoencoder, or can be thought of as a single-hidden-layer generative neural network. We thus consider it a basal generative representation learner that can be used as a minimal model for st…

• A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility

  Gunn Kim · 30 juin 2026

  We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories. In the local regime where latent dynamics admit an effective Markovian des…

• Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space Divergences

  Ziyu Chen, Markos A. Katsoulakis, Benjamin J. Zhang · 30 juin 2026

  We introduce a novel Wasserstein-1 ($W_1$) path-space divergence for stochastic and deterministic dynamics and establish a Wasserstein Uncertainty Propagation (WUP) theorem that bounds the $W_1$ distance between terminal distributions by the proposed divergence, equivalently characterized by a weigh…

• Counterfactual Residual Data Augmentation for Regression

  Hossein Mohebbi, Oliver Schulte, Ke Li, Pascal Poupart · 30 juin 2026

  Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations. Inspired by the impact of data augmentation in vision and language, we propose a novel Counterfactual Residual Data Augmentation (CRDA) technique for tabula…

• Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

  Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger, Wieland Brendel, Martin Jaggi · 30 juin 2026

  Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong length generalization beyond the length of training sequences, this behavior is brittle, yielding high out-of-distributio…

• Constrained Tabular Diffusion for Finance

  Michael Cardei, Jose M Munoz, Oscar Barrera, Shreyas K Chandrahas, Partha Saha · 30 juin 2026

  Generative models in finance face the dual challenge of producing realistic data while satisfying strict regulatory and economic objectives, a requirement that standard tabular diffusion models cannot provide. To address this difficulty, we introduce Constrained Tabular Diffusion for Finance (CTDF),…

• Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment

  Chen Wang, Peiran Yun, Pan Xie, Ke Deng · 30 juin 2026

  Diffusion and continuous-flow generative models achieve high-quality generation, and their deterministic sampling can be formulated as solving learned ODE dynamics. However, accurate ODE discretization often requires many steps, making efficient few-step generation a key challenge. Among acceleratio…

• StableMotion: One-Step Motion Estimation with Diffusion Prior

  Ziyi Wang, Haipeng Li, Lin Sui, Tianhao Zhou, Hai Jiang, Lang Nie, Bing Zeng, Shuaicheng Liu · 29 juin 2026

  We present StableMotion, a novel framework that leverages geometric and content priors from pretrained large-scale image diffusion models for motion estimation in single-image rectification tasks such as Stitched Image Rectangling (SIR) and Rolling Shutter Correction (RSC). Specifically, StableMotio…

• VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

  Kijung Jeon, Thuy-Duong Vuong, Molei Tao · 29 juin 2026

  Inference-time scaling is a promising paradigm to improve generative models, especially when outputs must satisfy structural constraints or optimize downstream rewards. We consider Masked Diffusion Model (MDM) and introduce MDM-VGB, a discrete diffusion sampler that augments unmasking generation wit…

• Accelerating Hierarchical Sparse Predictive Coding with Hybrid Amortized Inference

  Kazuhisa Fujita · 29 juin 2026

  Hierarchical predictive coding provides an interpretable framework for perception as error-driven inference in multi-layer generative models, while sparse coding imposes parsimonious latent representations through explicit sparsity constraints. Their combination yields hierarchical sparse predictive…

• Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding

  Dimitrios Bralios, Paris Smaragdis, Minje Kim · 29 juin 2026

  Neural audio autoencoders have become a core component of compression, feature extraction, and generation. However, while existing systems support variable bitrate, the vast majority of models still operate at a fixed latent frame-rate, allocating equal temporal budget to regions with very different…

• A Gaussian Perspective for Distributional Discrepancy in Generative Diffusion Models

  Qiang Sun, H. Vincent Poor, Wenyi Zhang · 29 juin 2026

  This paper introduces an analytical approach to quantifying and optimizing the distributional discrepancy in generative diffusion models. For a multivariate Gaussian source, we explicitly derive the closed-form evolution trajectory and the resulting Kullback-Leibler (KL) divergence between the distr…

• Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing

  Shubham Aggarwal · 29 juin 2026

  Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth. In this work, we identify this uniform allocation as a fundamental structural bottlenec…

• Class-frequency Guided Noise Schedule for Diffusion Models

  Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaojuan Qi, Bei Yu, Hanwang Zhang · 29 juin 2026

  In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within diffusion models. For score-based generative models, low-density regions often lead to inaccurately estimated scores, thereby compromising the generation quality. Although th…