Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling

  Marco Baiesi, Alberto Rosso · 15. Dezember 2025

  We show that nonequilibrium dynamics can play a constructive role in unsupervised machine learning by inducing the spontaneous emergence of latent-state cycles. We introduce a model in which visible and hidden variables interact through two independently parametrized transition matrices, defining a …

• Features Emerge as Discrete States: The First Application of SAEs to 3D Representations

  Albert Miao, Chenliang Zhou, Jiawei Zhou, Cengiz Oztireli · 15. Dezember 2025

  Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance. However, this technique has rarely been applied outside of the text…

• Flowception: Temporally Expansive Flow Matching for Video Generation

  Tariq Berrada Ifriqi, John Nguyen, Karteek Alahari, Jakob Verbeek, Ricky T. Q. Chen · 15. Dezember 2025

  We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive methods, Flowception alleviates error accumulation/drift as …

• Generalized Denoising Diffusion Codebook Models (gDDCM): Tokenizing images using a pre-trained diffusion model

  Fei Kong · 15. Dezember 2025

  Denoising diffusion models have emerged as a dominant paradigm in image generation. Discretizing image data into tokens is a critical step for effectively integrating images with Transformer and other architectures. Although the Denoising Diffusion Codebook Models (DDCM) pioneered the use of pre-tra…

• VFMF: World Modeling by Forecasting Vision Foundation Model Features

  Gabrijel Boduljak, Yushi Lan, Christian Rupprecht, Andrea Vedaldi · 15. Dezember 2025

  Forecasting from partial observations is central to world modeling. Many recent methods represent the world through images, and reduce forecasting to stochastic video generation. Although such methods excel at realism and visual fidelity, predicting pixels is computationally intensive and not direct…

• OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis

  Xiang Fan, Sharath Girish, Vivek Ramanujan, Chaoyang Wang, Ashkan Mirzaei, Petr Sushko, Aliaksandr Siarohin, Sergey Tulyakov, Ranjay Krishna · 12. Dezember 2025

  Prior approaches injecting camera control into diffusion models have focused on specific subsets of 4D consistency tasks: novel view synthesis, text-to-video with camera control, image-to-video, amongst others. Therefore, these fragmented approaches are trained on disjoint slices of available 3D/4D …

• Bidirectional Normalizing Flow: From Data to Noise and Back

  Yiyang Lu, Qiao Sun, Xianbang Wang, Zhicheng Jiang, Hanhong Zhao, Kaiming He · 12. Dezember 2025

  Normalizing Flows (NFs) have been established as a principled framework for generative modeling. Standard NFs consist of a forward process and a reverse process: the forward process maps data to noise, while the reverse process generates samples by inverting it. Typical NF forward transformations ar…

• Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment

  Sangha Park, Eunji Kim, Yeongtak Oh, Jooyoung Choi, Sungroh Yoon · 12. Dezember 2025

  Despite substantial progress in text-to-image generation, achieving precise text-image alignment remains challenging, particularly for prompts with rich compositional structure or imaginative elements. To address this, we introduce Negative Prompting for Image Correction (NPC), an automated pipeline…

• Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality

  Lingjing Kong, Shaoan Xie, Guangyi Chen, Yuewen Sun, Xiangchen Song, Eric P. Xing, Kun Zhang · 12. Dezember 2025

  Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque black boxes, hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show remarkable empirical success, they often lack theoretical guarantees, …

• CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models

  Tong Zhang, Carlos Hinojosa, Bernard Ghanem · 12. Dezember 2025

  Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-time mitigation methods typically manipulate classifier-free guidance (CFG) or perturb prompt embeddings; however, they oft…

• Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative Models

  Defang Chen, Zhenyu Zhou, Can Wang, Siwei Lyu · 12. Dezember 2025

  Diffusion-based generative models employ stochastic differential equations (SDEs) and their equivalent probability flow ordinary differential equations (ODEs) to establish a smooth transformation between complex high-dimensional data distributions and tractable prior distributions. In this paper, we…

• AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generation

  Sharath Girish, Viacheslav Ivanov, Tsai-Shien Chen, Hao Chen, Aliaksandr Siarohin, Sergey Tulyakov · 12. Dezember 2025

  Recent advances in subject-driven video generation with large diffusion models have enabled personalized content synthesis conditioned on user-provided subjects. However, existing methods lack fine-grained temporal control over subject appearance and disappearance, which are essential for applicatio…

• MotionEdit: Benchmarking and Learning Motion-Centric Image Editing

  Yixin Wan, Lei Ke, Wenhao Yu, Kai-Wei Chang, Dong Yu · 12. Dezember 2025

  We introduce MotionEdit, a novel dataset for motion-centric image editing-the task of modifying subject actions and interactions while preserving identity, structure, and physical plausibility. Unlike existing image editing datasets that focus on static appearance changes or contain only sparse, low…

• Stronger Normalization-Free Transformers

  Mingzhi Chen, Taiming Lu, Jiachen Zhu, Mingjie Sun, Zhuang Liu · 12. Dezember 2025

  Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) has demonstrated that alternatives are possible. The point-wise function DyT constrains extreme values for stable convergence and reaches norm…

• What matters for Representation Alignment: Global Information or Spatial Structure?

  Jaskirat Singh, Xingjian Leng, Zongze Wu, Liang Zheng, Richard Zhang, Eli Shechtman, Saining Xie · 12. Dezember 2025

  Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target representation matters for generation, its \textit{global} \revision{…

• Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants

  Chirag Modi, Jiequn Han, Eric Vanden-Eijnden, Joan Bruna · 12. Dezember 2025

  Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe measurements corrupted through a noisy, ill-conditioned channel. A gen…

• Disentangled and Distilled Encoder for Out-of-Distribution Reasoning with Rademacher Guarantees

  Zahra Rahiminasab, Michael Yuhas, Arvind Easwaran · 12. Dezember 2025

  Recently, the disentangled latent space of a variational autoencoder (VAE) has been used to reason about multi-label out-of-distribution (OOD) test samples that are derived from different distributions than training samples. Disentangled latent space means having one-to-many maps between latent dime…

• MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical Metadata

  Yihao Liu, Chenyu Gao, Lianrui Zuo, Michael E. Kim, Brian D. Boyd, Lisa L. Barnes, Walter A. Kukull, Lori L. Beason-Held, Susan M. Resnick, Timothy J. Hohman, Warren D. Taylor, Bennett A. Landman · 12. Dezember 2025

  Modern deep learning methods have achieved impressive results across tasks from disease classification, estimating continuous biomarkers, to generating realistic medical images. Most of these approaches are trained to model conditional distributions defined by a specific predictive direction with a …

• Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling

  Tasmiah Haque, Md. Asif Bin Syed, Byungheon Jeong, Xue Bai, Sumit Mohan, Somdyuti Paul, Imtiaz Ahmed, Srinjoy Das · 12. Dezember 2025

  Motion Transfer is a technique that synthesizes videos by transferring motion dynamics from a driving video to a source image. In this work we propose a deep learning-based framework to enable real-time video motion transfer which is critical for enabling bandwidth-efficient applications such as vid…

• Targeted Data Protection for Diffusion Model by Matching Training Trajectory

  Hojun Lee, Mijin Koo, Yeji Song, Nojun Kwak · 12. Dezember 2025

  Recent advancements in diffusion models have made fine-tuning text-to-image models for personalization increasingly accessible, but have also raised significant concerns regarding unauthorized data usage and privacy infringement. Current protection methods are limited to passively degrading image qu…

• LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

  Huanlin Gao, Ping Chen, Fuyuan Shi, Chao Tan, Zhaoxiang Liu, Fang Zhao, Kai Wang, Shiguo Lian · 12. Dezember 2025

  We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local heuristic errors, they often overlook the accumulation of global errors, leading to noticeable content degradation between…

• Color encoding in Latent Space of Stable Diffusion Models

  Guillem Arias, Ariadna Sol\`a, Mart\'i Armengod, Maria Vanrell · 11. Dezember 2025

  Recent advances in diffusion-based generative models have achieved remarkable visual fidelity, yet a detailed understanding of how specific perceptual attributes - such as color and shape - are internally represented remains limited. This work explores how color is encoded in a generative model thro…

• FALCON: Few-step Accurate Likelihoods for Continuous Flows

  Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong · 11. Dezember 2025

  Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem by pairing a generative model, capable of exact likelihood computation, with importance sampling to obtain consistent samples under the tar…

• Aligning Text to Image in Diffusion Models is Easier Than You Think

  Jaa-Yeon Lee, Byunghee Cha, Jeongsol Kim, Jong Chul Ye · 11. Dezember 2025

  While recent advancements in generative modeling have significantly improved text-image alignment, some residual misalignment between text and image representations still remains. Some approaches address this issue by fine-tuning models in terms of preference optimization, etc., which require tailor…

• Constrained Discrete Diffusion

  Michael Cardei, Jacob K Christopher, Thomas Hartvigsen, Bhavya Kailkhura, Ferdinando Fioretto · 11. Dezember 2025

  Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these models present a new and important opportunity to enforce se…