Generative Adversarial Networks and Image Synthesis

Derniers papiers

• Disjoint Generation of Synthetic Data

  Anton Danholt Lautrup, Muhammad Rajabinasab, Tobias Hyrup, Arthur Zimek, Peter Schneider-Kamp · 9 juin 2026

  We propose a new framework for generating tabular synthetic datasets via disjoint generative models. In this paradigm, a dataset is partitioned into disjoint subsets that are supplied to separate instances of generative models. The results are then combined post hoc by a joining operation that works…

• Learning to Solve Generative ODEs Beyond the Linear Span

  Sihyeon Kim, Seunghun Lee, Vikas Singh, Hyunwoo J. Kim · 9 juin 2026

  Diffusion and flow generative models sample by integrating a learned ODE, but high quality still requires many sequential model evaluations. Solver learning reduces this cost by adapting scalar coefficients, timesteps, or both, while keeping the backbone model fixed. In this work, we identify a stru…

• BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension

  Tsung-Wei Pan, Jung-Hua Wang · 9 juin 2026

  Existing video generation frameworks treat sequence duration as an externally prescribed parameter -- fixed frame counts or text prompts -- producing clips whose temporal boundaries are decoupled from the statistical structure of real behavioral data. This assumption is fundamentally misaligned with…

• Self-Consistent Generative Paths via Admissible Random Variational Transport

  Lei Luo, Yingzhen Zhang, Jian Yang · 9 juin 2026

  Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map. Diffusion models follow stochastic denoising paths, flow matching learns transport fields, consistency and distillation methods compress paths into one or a few ste…

• When Do Local Score Models Extrapolate Across Size? A Diagnostic Theory and Benchmark

  Wenjie Xi · 9 juin 2026

  Scientific generative modeling often requires size transfer, where models trained on small systems are evaluated on larger ones. While translation-invariant architectures enable this evaluation, we show that architectural locality alone does not guarantee stable size extrapolation. Instead, stable e…

• Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation

  Qiaoyu Chen, Bing Zhang · 9 juin 2026

  Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations. Under optimization on limited samples, models overfit to local domain shortcuts. Fine-tuning massive weights on specialized data introduces erroneous inductive biases, in…

• Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

  Xiao Li, Yixuan Jia, Zekai Zhang, Xiang Li, Lianghe Shi, Jinxin Zhou, Zhihui Zhu, Liyue Shen, Qing Qu · 9 juin 2026

  Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored. Drawing inspiration from self-supervised learning (SSL), we introduce a framework for…

• What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction

  Jewon Yeom, Hanseul Kim, Jeongjae Park, Sungmok Jung, Jaejin Lee, Taesup Kim · 9 juin 2026

  Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces. We study this question through a unified probe-based evaluation across diverse encoder families, including …

• Where the Score Lives: A Wavelet View of Diffusion

  Emma Finn, Binxu Wang, T. Anderson Keller, Demba E. Ba · 9 juin 2026

  Score-based generative models have had remarkable success over the last decade in generating a diverse set of visually plausible images. A variety of architectures including CNNs, U-Nets, and Transformers have been used as the score-approximation network in such diffusion modeling; however, to date,…

• Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching

  Qianli Ma, Zhiqing Tang, Hanshuai Cui, Zhi Yao, Weijia Jia · 9 juin 2026

  Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (KV) caches often dominates time-to-first-token (TTFT). Moreover, reusing caches across heterogeneous models (e.g., base …

• Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark

  Muhammed Rasin · 9 juin 2026

  We study a capability the dominant paradigm in synthetic tabular data does not provide: exact satisfaction of a declared analytical outcome with no source data. Imitation methods (copulas, GANs, diffusion) learn a real distribution and sample from it, and are judged on fidelity to real data. A large…

• PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal Laws

  Danqi Zhuang, Jisui Huang, Xiaoyue Xi, Andrew Kiggins, Xiaojie Wang, Ke Chen, Yue Wu · 9 juin 2026

  Standard diffusion models typically use a single time-homogeneous Gaussian terminal distribution as the reference law for generation. While this choice is analytically convenient and empirically powerful, it provides little explicit structure for data concentrated near low-dimensional manifolds, whe…

• Assessing Sample Quality in Conditional Generation under Compositional Shift

  Berker Demirel, Valentino Maiorca, Marco Fumero, Theofanis Karaletsos, Francesco Locatello · 9 juin 2026

  Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimental factors. In many applications, especially in scientific domains, such models are attractive to explore conditions for …

• Disentanglement with Holographic Reduced Representations

  Jhonny J. Velasquez Olivera, Christo K. Thomas, Walid Saad · 9 juin 2026

  Disentanglement, the separation of factors of variation in data using neural networks, remains a long-standing challenge in machine learning. Prior work has addressed this problem with variational autoencoders and generative adversarial networks that incorporate ideas from variational inference and …

• IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment

  Zichen Zhu, Yuheng Sun, Mingxuan Zhu, Wenjie Ma, Situo Zhang, Zhexiang Wang, Ziyue Yang, Danyang Zhang, Kunyao Lan, Zihan Zhao, Dingye Liu, Siqi Xiang, Lu Chen, Kai Yu · 9 juin 2026

  Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes. Creations by generative models may contain artifacts, implausible details, or stylistic drift away from photorealism and offer little insight into why an edit was …

• Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation

  Xuanyi Liu, Deyi Ji, Junyu Lu, Jing Wang, Qianxiong Xu, Xuhang Chen, Tianrun Chen, Siwei Ma · 9 juin 2026

  Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts. Existing approaches primarily polish the prompt for fluency and readability. However, the enhancement process still lacks visual grounding. As …

• MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation

  Ishaan Preetam Chandratreya, David Charatan, Basile Van Hoorick, Sergey Zakharov, Vitor Guizilini, Phillip Isola, Vincent Sitzmann · 9 juin 2026

  Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence lengths. We show that this issue can be mitigated by generating video using coarse-to-fine rollout with…

• DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression

  Hongxu Ma, Lin Wang, Chenghou Jin, Han Zhou, Jie Zhang, Xiaoyu Yang, Chunjie Chen, Jihong Guan, Shuigeng Zhou · 9 juin 2026

  Ordinal Regression (OR) aims to predict target values with inherent order, underpinning critical applications across diverse domains, from recommender systems to computer vision. Though having evolved from naive regression to discretization-based classification and generation, existing paradigms rem…

• WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing

  Young D. Kwon, Miles Williams, Rui Li, Alexandros Kouris, Stylianos I. Venieris · 9 juin 2026

  The autoregressive nature of large language models (LLMs) remains a significant bottleneck for inference, particularly in complex agentic workloads. While speculative decoding (SD) accelerates inference, current approaches rely on static drafting paradigms, utilising either autoregressive drafting m…

• Neural Field Tokenizations with Hierarchy and Spatial Locality Priors

  Alonso Urbano, David W. Romero, Max Zimmer, Sebastian Pokutta · 9 juin 2026

  Neural fields parameterize data as functions from coordinates to values, providing a unified framework for representation learning across modalities. Existing approaches are dominated by per-sample meta-learning, which scales poorly due to memory-intensive inner-loop optimization. The natural altern…

• Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects

  Hwiyeong Lee, Ingyu Bang, Uiji Hwang, Hyelim Lim, Taeuk Kim · 9 juin 2026

  While sparse autoencoders provide features more interpretable than individual neurons, reliably characterizing them remains challenging. We propose Query Lens, which extends Logit Lens to enable more comprehensive and faithful interpretations of sparse features. By jointly considering encoder-side k…

• Anchor-Conditioned Compositional Control for Landscape Image Generation

  Gadha Lekshmi P, Govind Arun, Rohith Syam, Ahmed Elgammal · 9 juin 2026

  Image generative models, though widely used as creative tools, offer limited support for the kind of compositional control that photographers and visual artists routinely exercise. This paper presents early results on an anchor conditioned finetuning framework for landscape image generation, in whic…

• Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis

  Samuele Punzo, Niccol\`o Caselli, Ippokratis Pantelidis, Francesco Massafra, Salvatore Lo Sardo, Mohammadreza Salehi · 9 juin 2026

  We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information varies across model families, layers, and probe types. Using frozen-feature probing on IntPhys2 and Minimal Video Pairs (MVP), we compare predictive join…

• BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation

  Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali, Gianfranco Doretto, Donald A. Adjeroh · 9 juin 2026

  High-Dimensional Low-Sample Size (HDLSS) tabular domains (e.g., omics) are characterized by $n \ll m$, where $n$ = number of samples, and $m$ = number of features. Such domains often exhibit strong local correlation groups, sparse cross-group dependencies, heavy-tailed non-Gaussian marginals, hetero…

• Generation Properties of Stochastic Interpolation under Finite Training Set

  Yunchen Li, Shaohui Lin, Zhou Yu · 9 juin 2026

  This paper investigates the theoretical behavior of generative models under finite training populations. Within the stochastic interpolation generative framework, we derive closed-form expressions for the optimal velocity field and score function when only a finite number of training samples are ava…