Generative Adversarial Networks and Image Synthesis

Latest papers

• EVODiff: Entropy-aware Variance Optimized Diffusion Inference

  Shigui Li, Wei Chen, Delu Zeng · 28 October 2025

  Diffusion models (DMs) excel in image generation, but suffer from slow inference and the training-inference discrepancies. Although gradient-based solvers like DPM-Solver accelerate the denoising inference, they lack theoretical foundations in information transmission efficiency. In this work, we in…

• ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation

  Yunhong Min, Daehyeon Choi, Kyeongmin Yeo, Jihyun Lee, Minhyuk Sung · 28 October 2025

  We introduce ORIGEN, the first zero-shot method for 3D orientation grounding in text-to-image generation across multiple objects and diverse categories. While previous work on spatial grounding in image generation has mainly focused on 2D positioning, it lacks control over 3D orientation. To address…

• Distributional Autoencoders Know the Score

  Andrej Leban · 28 October 2025

  The Distributional Principal Autoencoder (DPA) combines distributionally correct reconstruction with principal-component-like interpretability of the encodings. In this work, we provide exact theoretical guarantees on both fronts. First, we derive a closed-form relation linking each optimal level-se…

• Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations

  Tal Barami, Nimrod Berman, Ilan Naiman, Amos H. Hason, Rotem Ezra, Omri Azencot · 28 October 2025

  Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors over time, prior work has mostly focused on simpler two-factor static and dynamic s…

• Score-based Generative Neural Networks for Large-Scale Optimal Transport

  Mara Daniels, Tyler Maunu, Paul Hand · 28 October 2025

  We consider the fundamental problem of sampling the optimal transport coupling between given source and target distributions. In certain cases, the optimal transport plan takes the form of a one-to-one mapping from the source support to the target support, but learning or even approximating such a m…

• It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited Steps

  Pedro Cisneros-Velarde · 28 October 2025

  We consider the situation where we have a limited number of denoising steps, i.e., of evaluations of a diffusion model. We show that two parallel processors or samplers under such limitation can improve the quality of the sampled image. Particularly, the two samplers make denoising steps at successi…

• Simple Denoising Diffusion Language Models

  Huaisheng Zhu, Zhengyu Chen, Shijie Zhou, Zhihui Xie, Yige Yuan, Zhimeng Guo, Siyuan Xu, Hangfan Zhang, Vasant Honavar, Teng Xiao · 28 October 2025

  Diffusion models have recently been extended to language generation through Masked Diffusion Language Models (MDLMs), which achieve performance competitive with strong autoregressive models. However, MDLMs tend to degrade in the few-step regime and cannot directly adopt existing few-step distillatio…

• On the Anisotropy of Score-Based Generative Models

  Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti · 28 October 2025

  We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce the Score Anisotropy Directions (SADs), architecture-dependent directions that reveal how different networks preferentially capture data structure. Our a…

• MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification

  Luca Caldera, Giacomo Bottacini, Lara Cavinato · 28 October 2025

  Generative modeling has emerged as a powerful paradigm for representation learning, but its direct applicability to challenging fields like medical imaging remains limited: mere generation, without task alignment, fails to provide a robust foundation for clinical use. We propose MAGIC-Flow, a condit…

• Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing

  Iskander Azangulov, Teodora Pandeva, Niranjani Prasad, Javier Zazo, Sushrut Karmalkar · 28 October 2025

  Masked diffusion models (MDMs) offer a compelling alternative to autoregressive models (ARMs) for discrete text generation because they enable parallel token sampling, rather than sequential, left-to-right generation. This means potentially much faster inference. However, effective parallel sampling…

• Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge

  Nimrod Berman, Omkar Joglekar, Eitan Kosman, Dotan Di Castro, Omri Azencot · 28 October 2025

  Recent advances in generative modeling have positioned diffusion models as state-of-the-art tools for sampling from complex data distributions. While these models have shown remarkable success across single-modality domains such as images and audio, extending their capabilities to Modality Translati…

• GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection

  Xin Gao, Jiyao Liu, Guanghao Li, Yueming Lyu, Jianxiong Gao, Weichen Yu, Ningsheng Xu, Liang Wang, Caifeng Shan, Ziwei Liu, Chenyang Si · 28 October 2025

  Recent advancements have explored text-to-image diffusion models for synthesizing out-of-distribution (OOD) samples, substantially enhancing the performance of OOD detection. However, existing approaches typically rely on perturbing text-conditioned embeddings, resulting in semantic instability and …

• CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing

  Weiyan Xie, Han Gao, Didan Deng, Kaican Li, April Hua Liu, Yongxiang Huang, Nevin L. Zhang · 28 October 2025

  Recent advances in text-to-image (T2I) models have enabled training-free regional image editing by leveraging the generative priors of foundation models. However, existing methods struggle to balance text adherence in edited regions, context fidelity in unedited areas, and seamless integration of ed…

• Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

  Anlin Zheng, Xin Wen, Xuanyang Zhang, Chuofan Ma, Tiancai Wang, Gang Yu, Xiangyu Zhang, Xiaojuan Qi · 28 October 2025

  In this work, we present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model, which is a largely underexplored area. Specifically, we employ a frozen vision foundation model as the encoder of our tokenizer. To enhance its effectiveness, we introduce two …

• Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries

  Haoxiang Wang, Zinan Lin, Da Yu, Huishuai Zhang · 28 October 2025

  Generating high fidelity, differentially private (DP) synthetic images offers a promising route to share and analyze sensitive visual data without compromising individual privacy. However, existing DP image synthesis methods struggle to produce high resolution outputs that faithfully capture the str…

• Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models

  Taehoon Yoon, Yunhong Min, Kyeongmin Yeo, Minhyuk Sung · 28 October 2025

  We introduce $\Psi$-Sampler, an SMC-based framework incorporating pCNL-based initial particle sampling for effective inference-time reward alignment with a score-based generative model. Inference-time reward alignment with score-based generative models has recently gained significant traction, follo…

• Variational Masked Diffusion Models

  Yichi Zhang, Alex Schwing, Zhizhen Zhao · 28 October 2025

  Masked diffusion models have recently emerged as a flexible framework for discrete generative modeling. However, a key limitation of standard masked diffusion is its inability to effectively capture dependencies among tokens that are predicted concurrently, leading to degraded generation quality whe…

• Nested AutoRegressive Models

  Hongyu Wu, Xuhui Fan, Zhangkai Wu, Longbing Cao · 28 October 2025

  AutoRegressive (AR) models have demonstrated competitive performance in image generation, achieving results comparable to those of diffusion models. However, their token-by-token image generation mechanism remains computationally intensive and existing solutions such as VAR often lead to limited sam…

• Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

  Marianne Arriola, Yair Schiff, Hao Phung, Aaron Gokaslan, Volodymyr Kuleshov · 28 October 2025

  Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network at every denoising step and incur high computational cost. Ou…

• Scaling Non-Parametric Sampling with Representation

  Vincent Lu, Aaron Truong, Zeyu Yun, Yubei Chen · 28 October 2025

  Scaling and architectural advances have produced strikingly photorealistic image generative models, yet their mechanisms still remain opaque. Rather than advancing scaling, our goal is to strip away complicated engineering tricks and propose a simple, non-parametric generative model. Our design is g…

• Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation

  Bailey Trang, Parham Saremi, Alan Q. Wang, Fangrui Huang, Zahra TehraniNasab, Amar Kumar, Tal Arbel, Li Fei-Fei, Ehsan Adeli · 28 October 2025

  Capturing diversity is crucial in conditional and prompt-based image generation, particularly when conditions contain uncertainty that can lead to multiple plausible outputs. To generate diverse images reflecting this diversity, traditional methods often modify random seeds, making it difficult to d…

• Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications

  Shamim Yazdani, Akansha Singh, Nripsuta Saxena, Zichong Wang, Avash Palikhe, Deng Pan, Umapada Pal, Jie Yang, Wenbin Zhang · 28 October 2025

  In recent years, deep learning based generative models, particularly Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models (DMs), have been instrumental in in generating diverse, high-quality content across various domains, such as image and video synthesis. T…

• Variance-Reduction Guidance: Sampling Trajectory Optimization for Diffusion Models

  Shifeng Xu, Yanzhu Liu, Adams Wai-Kin Kong · 28 October 2025

  Diffusion models have become emerging generative models. Their sampling process involves multiple steps, and in each step the models predict the noise from a noisy sample. When the models make prediction, the output deviates from the ground truth, and we call such a deviation as \textit{prediction e…

• Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models

  Guo Li, Yuyang Yu, Xuemiao Xu · 28 October 2025

  Diffusion models have demonstrated powerful performance in generating high-quality images. A typical example is text-to-image generator like Stable Diffusion. However, their widespread use also poses potential privacy risks. A key concern is membership inference attacks, which attempt to determine w…

• Proportion and Perspective Control for Flow-Based Image Generation

  Julien Boudier, Hugo Caselles-Dupr\'e · 28 October 2025

  While modern text-to-image diffusion models generate high-fidelity images, they offer limited control over the spatial and geometric structure of the output. To address this, we introduce and evaluate two ControlNets specialized for artistic control: (1) a proportion ControlNet that uses bounding bo…