Generative Adversarial Networks and Image Synthesis

Latest papers

• Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression

  Silas Koemen · 3 August 2026

  Tree-based diffusion models fit flexible conditional predictive distributions for tabular regression without a neural density estimator, but they inherit their design defaults---noising path, parameterization, training distribution, features, sampler---from the neural setting. We show these defaults…

• WaiT for the Signal: Simple Frequency-Aware Flow-Matching

  Krunoslav Lehman Pavasovic, Th\'eophane Vallaeys, St\'ephane Mallat, Giulio Biroli, Luke Zettlemoyer, Brian Karrer, Jakob Verbeek · 3 August 2026

  As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality. However, standard flow matching treats all spatial frequencies uniformly, ignoring the natural frequency hierarchy where high-frequency bands…

• FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents

  Nitish Nagesh, Mahdi Bagheri, Amir M. Rahmani · 3 August 2026

  Synthetic tabular data is increasingly used in privacy-preserving data sharing, data augmentation, and to mitigate downstream classifier bias. State-of-the-art tabular diffusion models such as TabDDPM and TabSyn achieve excellent distributional fidelity but offer no mechanism for fairness; conversel…

• MBDiff: Multi-view Behavior-aware Diffusion Model for Probabilistic Utility Data Imputation

  Rongchao Xu, Lin Jiang, Dahai Yu, Ximiao Li, Guang Wang · 3 August 2026

  Utility data (e.g., electricity, water, and gas consumption), collected by ubiquitous sensors and embedded devices, often contains substantial missing values due to various factors such as device failures and data transmission issues. The data missingness can severely impact utility billing accuracy…

• Detecting AI-Generated Videos with Spiking Neural Networks

  Minsuk Jang, Yujin Yang, Hee-Seon Kim, Minseok Son, Younghun Kim, Changick Kim · 3 August 2026

  Modern AI-generated videos are photorealistic at the single-frame level, leaving inter-frame dynamics as the main remaining axis for detection. Existing detectors typically handle this temporal evidence in three ways: feeding the full frame sequence to a generic temporal backbone, reducing one domin…

• From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models

  Seunggeun Kim, Jaeyeon Kim, Taekyun Lee, Yuyuan Chen, Yilun Du, Sham Kakade, Sitan Chen · 30 July 2026

  Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a process we call any-order inference. For autoregressive language models, which lack a native any-order interface, non-causal abilities such as infilli…

• Amortized Moment Matching for Visual Generation

  Wenze Liu, Xintao Wang, Pengfei Wan, Xiangyu Yue · 30 July 2026

  We propose amortized moment matching, utilizing neural networks to learn data moments as distributional training signals. By casting diffusion denoisers through polynomial projections, we establish a general framework for moment amortization, revealing that an $n$-th degree projection explicitly ide…

• Flow Map Learning via Nongradient Vector Flow

  Mark Goldstein, Anshuk Uppal, Raghav Singhal, Aahlad Puli, Rajesh Ranganath · 30 July 2026

  Diffusion and flow-based models benefit from simple regression losses, but inference incurs significant overhead because sampling requires integration. Consistency models address this by directly learning the flow maps along the ODE trajectory, opening a design space between one-step and many-step a…

• Mitigating Compounding Error via Video Representation Regularization

  Taiye Chen, Qi Zhang, Yisen Wang · 30 July 2026

  Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window autoregressive inference suffers from severe error accumulation that degrades frame quality over time. Although this phenomenon has been widely obs…

• FloDR: An invertible dimensionality reduction method based on a normalising flow

  Abdallah Baraka, Daniel Probst · 30 July 2026

  It is common for two-dimensional embeddings of high-dimensional data to be read far beyond what they can support. Distances in and between clusters, the meaning behind empty spaces, and the amount of structure hidden at each point are generally invisible in the output of methods such as t-SNE and UM…

• Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives

  Xiaolong Liu, Junjian Li, Yuan Xiao, Jiaqi Deng, Dayong Ye, Tianqing Zhu, Huan Huo · 30 July 2026

  Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without extensive prompt engineering. However, existing prompt inversion methods suffer from significant limitations: (1) gradient-based methods are unstab…

• PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention

  Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Jesson Wang, Siheng Wang, Guang Yang, Haoyan Xu, Chenhao Wei, Zhengqing Yuan, Youran Shen, Yanfang Ye, Junhao Dong · 29 July 2026

  Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising. We study this problem at the level of attention rather than claiming AR-weight reus…

• Parallel Decoding Distillation for Fast Image and Video Generation

  Neta Shaul, Chao Liu, Arash Vahdat, Julius Berner · 29 July 2026

  Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA) acceleration methods heavily rely on variational score distillation (VSD) and adversarial losses to distill diffusion models into few-step generat…

• Physics-Grounded Fluid Video Generation with a Simulation Dataset and Dual-Stream Optical-Flow Supervision

  Ruijie Su, Yuanzhi Liang, Xiaohua Xie, Jianhuang Lai · 29 July 2026

  Video diffusion models generate visually compelling content but routinely violate elementary physics when the subject involves fluids: liquid columns break apart in mid-air, container water levels fail to rise as liquid is poured in, and splashes disperse without regard to momentum or gravity. We at…

• Soft-Constrained Optimization of Latent Space in Variational Autoencoders

  Ye Shi · 28 July 2026

  The usefulness of a variational autoencoder (VAE) depends on two properties of its latent space that are hard to obtain together: high encoding capacity in the individual latent variables, and a low-dimensional, disentangled organization of those variables. Weakening the Kullback-Leibler regularizat…

• Exploration of the generative capabilities of Boltzmann machines applied to social systems under the majority rule

  Mauricio A. Valle, Gonzalo A. Ruz · 28 July 2026

  We study the generative capabilities of Boltzmann machines to recover systems governed by the majority rule under critical conditions. To this end, we train deep belief networks (DBNs) with different configurations, where the first layer can use Gaussian visible units with more than two states (i.e.…

• A Coulomb Particle Model for Learning Kernel Attention in Transformers

  Masoud Badiei Khuzani, Sharath Honnaiah, Atiq Islam, Alex Cozzi, Abraham Bagherjeiran · 28 July 2026

  Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution. We propose a particle-based method that learns this distribution by optimizing kernel-target alignment while regularizing particles with a Riesz/Coul…

• Beyond ICA: Identifiability by Symmetry Breaking

  Pengzhou Wu · 28 July 2026

  We prove the identifiability of deep generative models (DGMs) with piecewise-affine (PWA) decoders and Gaussian mixture model (GMM) priors, in a purely unsupervised setting. We introduce three algebraic contrast principles for symmetry breaking: domain contrast, which trivializes the mixture symmetr…

• Joint Flow Matching for Generator-Consistent Classification

  Hayden McAlister, Lech Szymanski · 28 July 2026

  We introduce Joint Flow Matching (JFM), a training framework for continuous normalising flows over multiple variables. Standard flow matching transports variables from noise to data simultaneously, offering no natural mechanism for forward and reverse conditional inference from a shared joint model.…

• Physics-Guided Generative AI for Property-Targeted 3D Porous Media Design

  Peng Wang · 28 July 2026

  Inverse design of three-dimensional porous media is central to applications in filtration, catalysis, energy storage, fuel cells, thermal management, and biomedical scaffolds, but remains challenging because many distinct pore geometries can share similar porosity or permeability while small structu…

• Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data

  Yuefei Shen, Xiaotong Shen · 28 July 2026

  Mixed continuous--categorical data pose a representation problem for continuous generative models. Flow Matching and Gaussian diffusion operate in Euclidean spaces, whereas categorical laws lie on probability simplices and may be highly imbalanced. We study a logit-coordinate framework that encodes …

• All in One: Generative Modeling as Mean-Field Game Design

  Kun Zhao, Xu Chen · 28 July 2026

  Mean-field games (MFGs) offer a unifying lens on continuous-time generative modeling: a cost tuple recovering twelve prominent models---Continuous Normalizing Flows, OT-Flow, Score-based Models, Schr\"{o}dinger Bridges, and more---as special cases of one variational problem. Yet two dimensions of th…

• From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models

  Jinshu Huang, Yiming Jiang, Chunlin Wu · 28 July 2026

  Despite the empirical success of score-based diffusion models, a complete theoretical understanding of how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality remains underdeveloped. Existing sampling analyses often evaluate the generativ…

• UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

  Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang, Wei Liu, Yi Zhu, Zuoqiang Shi, Pipi Hu · 28 July 2026

  Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remains editable during sampling. However, adapting AR checkpoints across corruption kernels remains challenging because exis…

• FILLER: Feature Imputation via Latent Location Exploration and Retrieval

  Santu Mondal, Chayan Maitra, Rajat K. De · 28 July 2026

  In real-world machine learning applications, incomplete observations create a fundamental challenge. Researchers have come up with several ideas to address this crucial problem. However, current models still face challenges in balancing scalability and structural consistency. This study proposes a f…