Generative Adversarial Networks and Image Synthesis

Latest papers

• Enhancing diffusion models with Gaussianization preprocessing

  Li Cunzhi, Louis Kang, Hideaki Shimazaki · 25 December 2025

  Diffusion models are a class of generative models that have demonstrated remarkable success in tasks such as image generation. However, one of the bottlenecks of these models is slow sampling due to the delay before the onset of trajectory bifurcation, at which point substantial reconstruction begin…

• Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty

  Ziyu Chen, Xinbei Jiang, Peng Sun, Tao Lin · 25 December 2025

  Masked Diffusion Models (MDMs) offer flexible, non-autoregressive generation, but this freedom introduces a challenge: final output quality is highly sensitive to the decoding order. We are the first to formalize this issue, attributing the variability in output quality to the cumulative predictive …

• Generalization of Diffusion Models Arises with a Balanced Representation Space

  Zekai Zhang, Xiao Li, Xiang Li, Lianghe Shi, Meng Wu, Molei Tao, Qing Qu · 25 December 2025

  Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective. We analyze the distinctions between memorization and generalization in diffusion models through the lens of representation learning. By investigating a t…

• Diffusion Models in Simulation-Based Inference: A Tutorial Review

  Jonas Arruda, Niels Bracher, Ullrich K\"othe, Jan Hasenauer, Stefan T. Radev · 25 December 2025

  Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from simulated and real data. Their score-based formulation offers a flexible way to learn conditional or joint distributions over parameters a…

• Understanding Scaling Laws in Deep Neural Networks via Feature Learning Dynamics

  Zihan Yao, Ruoyu Wu, Tianxiang Gao · 25 December 2025

  The empirical success of deep learning is often attributed to scaling laws that predict consistent gains as model, data, and compute grow; however, large models can exhibit training instability and diminishing returns, suggesting that scaling laws describe what success looks like but not when and wh…

• Dominating vs. Dominated: Generative Collapse in Diffusion Models

  Hayeon Jeong, Jong-Seok Lee · 25 December 2025

  Text-to-image diffusion models have drawn significant attention for their ability to generate diverse and high-fidelity images. However, when generating from multi-concept prompts, one concept token often dominates the generation, suppressing the others-a phenomenon we term the Dominant-vs-Dominated…

• How I Met Your Bias: Investigating Bias Amplification in Diffusion Models

  Nathan Roos, Ekaterina Iakovleva, Ani Gjergji, Vito Paolo Pastore, Enzo Tartaglione · 24 December 2025

  Diffusion-based generative models demonstrate state-of-the-art performance across various image synthesis tasks, yet their tendency to replicate and amplify dataset biases remains poorly understood. Although previous research has viewed bias amplification as an inherent characteristic of diffusion m…

• PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models

  Mingue Park, Jisung Hwang, Seungwoo Yoo, Kyeongmin Yeo, Minhyuk Sung · 24 December 2025

  We introduce $\texttt{PairFlow}$, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a pretrained teacher. DFMs have recently emerged as a new class of generative models for discrete data, offering strong performance. However, the…

• Item Region-based Style Classification Network (IRSN): A Fashion Style Classifier Based on Domain Knowledge of Fashion Experts

  Jinyoung Choi, Youngchae Kwon, Injung Kim · 24 December 2025

  Fashion style classification is a challenging task because of the large visual variation within the same style and the existence of visually similar styles. Styles are expressed not only by the global appearance, but also by the attributes of individual items and their combinations. In this stud…

• PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior

  Wenhan Guo, Jinglun Yu, Yaning Wang, Jin U. Kang, Yu Sun · 23 December 2025

  Diffusion models are highly expressive image priors for Bayesian inverse problems. However, most diffusion models cannot operate on large-scale, high-dimensional data due to high training and inference costs. In this work, we introduce a Plug-and-play algorithm for 3D stochastic inference with laten…

• Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders

  Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky · 23 December 2025

  Sparse Autoencoders (SAEs) have demonstrated significant promise in interpreting the hidden states of language models by decomposing them into interpretable latent directions. However, training and interpreting SAEs at scale remains challenging, especially when large dictionary sizes are used. While…

• On Conditional Stochastic Interpolation for Generative Nonlinear Sufficient Dimension Reduction

  Shuntuo Xu, Zhou Yu, Jian Huang · 23 December 2025

  Identifying low-dimensional sufficient structures in nonlinear sufficient dimension reduction (SDR) has long been a fundamental yet challenging problem. Most existing methods lack theoretical guarantees of exhaustiveness in identifying lower dimensional structures, either at the population level or …

• What-If Decision Support for Product Line Extension Using Conditional Deep Generative Models

  Yinxing Li, Tsukasa Ishigaki · 23 December 2025

  Product line extension is a strategically important managerial decision that requires anticipating how consumer segments and purchasing contexts may respond to hypothetical product designs that do not yet exist in the market. Such decisions are inherently uncertain because managers must infer future…

• Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance

  Badr Moufad, Navid Bagheri Shouraki, Alain Oliviero Durmus, Thomas Hirtz, Eric Moulines, Jimmy Olsson, Yazid Janati · 23 December 2025

  Diffusion models have emerged as powerful priors for image editing tasks such as inpainting and local modification, where the objective is to generate realistic content that remains consistent with observed regions. In particular, zero-shot approaches that leverage a pretrained diffusion model, with…

• Generative Modeling through Spectral Analysis of Koopman Operator

  Yuanchao Xu, Fengyi Li, Masahiro Fujisawa, Youssef Marzouk, Isao Ishikawa · 23 December 2025

  We propose Koopman Spectral Wasserstein Gradient Descent (KSWGD), a generative modeling framework that combines operator-theoretic spectral analysis with optimal transport. The novel insight is that the spectral structure required for accelerated Wasserstein gradient descent can be directly estimate…

• Is Your Conditional Diffusion Model Actually Denoising?

  Daniel Pfrommer, Zehao Dou, Christopher Scarvelis, Max Simchowitz, Ali Jadbabaie · 23 December 2025

  We study the inductive biases of diffusion models with a conditioning-variable, which have seen widespread application as both text-conditioned generative image models and observation-conditioned continuous control policies. We observe that when these models are queried conditionally, their generati…

• Prototype-Guided Diffusion: Visual Conditioning without External Memory

  Bilal Faye, Hanane Azzag, Mustapha Lebbah · 23 December 2025

  Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods improve efficiency but rely on large memory banks, static similar…

• The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation

  Huiqi Deng, Qihan Ren, Zhuofan Chen, Zhenyuan Cui, Wen Shen, Peng Zhang, Hongbin Pei, Quanshi Zhang · 23 December 2025

  Understanding what kinds of cooperative structures deep neural networks (DNNs) can represent remains a fundamental yet insufficiently understood problem. In this work, we treat interactions as the fundamental units of such structure and investigate a largely unexplored question: how DNNs encode inte…

• InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion

  Hoiyeong Jin, Hyojin Jang, Jeongho Kim, Junha Hyung, Kinam Kim, Dongjin Kim, Huijin Choi, Hyeonji Kim, Jaegul Choo · 22 December 2025

  Recent advances in diffusion-based video generation have opened new possibilities for controllable video editing, yet realistic video object insertion (VOI) remains challenging due to limited 4D scene understanding and inadequate handling of occlusion and lighting effects. We present InsertAnywhere,…

• Easy Adaptation: An Efficient Task-Specific Knowledge Injection Method for Large Models in Resource-Constrained Environments

  Dong Chen, Zhengqing Hu, Shixing Zhao, Yibo Guo · 22 December 2025

  While the enormous parameter scale endows Large Models (LMs) with unparalleled performance, it also limits their adaptability across specific tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a critical approach for effectively adapting LMs to a diverse range of downstream tasks. However,…

• InfSplign: Inference-Time Spatial Alignment of Text-to-Image Diffusion Models

  Sarah Rastegar, Violeta Chatalbasheva, Sieger Falkena, Anuj Singh, Yanbo Wang, Tejas Gokhale, Hamid Palangi, Hadi Jamali-Rad · 22 December 2025

  Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training data and inability of text embeddings to encode spatial sema…

• The Diffusion Duality

  Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin Chiu, Volodymyr Kuleshov · 22 December 2025

  Uniform-state discrete diffusion models hold the promise of fast text generation due to their inherent ability to self-correct. However, they are typically outperformed by autoregressive models and masked diffusion models. In this work, we narrow this performance gap by leveraging a key insight: Uni…

• EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning

  Haoran Sun, Chen Cai, Huiping Zhuang, Kong Aik Lee, Lap-Pui Chau, Yi Wang · 22 December 2025

  The rapid development of deepfake video technology has not only facilitated artistic creation but also made it easier to spread misinformation. Traditional deepfake video detection (DVD) methods face issues such as a lack of transparency in their principles and insufficient generalization capabiliti…

• Disentangled representations via score-based variational autoencoders

  Benjamin S. H. Lyo, Eero P. Simoncelli, Cristina Savin · 22 December 2025

  We present the Score-based Autoencoder for Multiscale Inference (SAMI), a method for unsupervised representation learning that combines the theoretical frameworks of diffusion models and VAEs. By unifying their respective evidence lower bounds, SAMI formulates a principled objective that learns repr…

• Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

  Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky · 22 December 2025

  Sparse Autoencoders (SAEs) have demonstrated significant promise in interpreting the hidden states of language models by decomposing them into interpretable latent directions. However, training and interpreting SAEs at scale remains challenging, especially when large dictionary sizes are used. While…