Generative Adversarial Networks and Image Synthesis

Latest papers

• Panda: Test-Time Adaptation with Negative Data Augmentation

  Ruxi Deng, Wenxuan Bao, Tianxin Wei, Jingrui He · 14 November 2025

  Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data augmentation (PDA), which generates multiple views of each test sample …

• Boosted GFlowNets: Improving Exploration via Sequential Learning

  Pedro Dall'Antonia, Tiago da Silva, Daniel Augusto de Souza, C\'esar Lincoln C. Mattos, Diego Mesquita · 14 November 2025

  Generative Flow Networks (GFlowNets) are powerful samplers for compositional objects that, by design, sample proportionally to a given non-negative reward. Nonetheless, in practice, they often struggle to explore the reward landscape evenly: trajectories toward easy-to-reach regions dominate trainin…

• Computing Wasserstein Barycenters through Gradient Flows

  Eduardo Fernandes Montesuma, Yassir Bendou, Mike Gartrell · 14 November 2025

  Wasserstein barycenters provide a powerful tool for aggregating probability measures, while leveraging the geometry of their ambient space. Existing discrete methods suffer from poor scalability, as they require access to the complete set of samples from input measures. We address this issue by reca…

• Benchmarking Diversity in Image Generation via Attribute-Conditional Human Evaluation

  Isabela Albuquerque, Ira Ktena, Olivia Wiles, Ivana Kaji\'c, Amal Rannen-Triki, Cristina Vasconcelos, Aida Nematzadeh · 14 November 2025

  Despite advances in generation quality, current text-to-image (T2I) models often lack diversity, generating homogeneous outputs. This work introduces a framework to address the need for robust diversity evaluation in T2I models. Our framework systematically assesses diversity by evaluating individua…

• How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders

  Yiming Tang, Abhijeet Sinha, Dianbo Liu · 14 November 2025

  Although recent generative models are remarkably capable of producing instruction-following and realistic outputs, they remain prone to notable physical plausibility failures. Though critical in applications, these physical plausibility errors often escape detection by existing evaluation methods. F…

• Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising

  Assaf Singer, Noam Rotstein, Amir Mann, Ron Kimmel, Or Litany · 13 November 2025

  Diffusion-based video generation can create realistic videos, yet existing image- and text-based conditioning fails to offer precise motion control. Prior methods for motion-conditioned synthesis typically require model-specific fine-tuning, which is computationally expensive and restrictive. We int…

• Dataset-Free Weight-Initialization on Restricted Boltzmann Machine

  Muneki Yasuda, Ryosuke Maeno, Chako Takahashi · 13 November 2025

  In feed-forward neural networks, dataset-free weight-initialization methods such as LeCun, Xavier (or Glorot), and He initializations have been developed. These methods randomly determine the initial values of weight parameters based on specific distributions (e.g., Gaussian or uniform distributions…

• Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation

  Jing Wang, Wonho Bae, Jiahong Chen, Wenxu Wang, Junhyug Noh · 13 November 2025

  Recent work on latent diffusion models (LDMs) has focused almost exclusively on generative tasks, leaving their potential for discriminative transfer largely unexplored. We introduce Discriminative Vicinity Diffusion (DVD), a novel LDM-based framework for a more practical variant of source-free doma…

• A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning

  Shashank Gupta, Chaitanya Ahuja, Tsung-Yu Lin, Sreya Dutta Roy, Harrie Oosterhuis, Maarten de Rijke, Satya Narayan Shukla · 13 November 2025

  Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is the most popular choice of method for policy optimization. While effective in terms of performance, PPO is highly sensitive …

• RiemannFormer: A Framework for Attention in Curved Spaces

  Zhongping Ji · 13 November 2025

  This research endeavors to offer insights into unlocking the further potential of transformer-based architectures. One of the primary motivations is to offer a geometric interpretation for the attention mechanism in transformers. In our framework, the attention mainly involves metric tensors, tangen…

• Dynamic Diffusion Schr\"odinger Bridge in Astrophysical Observational Inversions

  Ye Zhu, Duo Xu, Zhiwei Deng, Jonathan C. Tan, Olga Russakovsky · 13 November 2025

  We study Diffusion Schr\"odinger Bridge (DSB) models in the context of dynamical astrophysical systems, specifically tackling observational inverse prediction tasks within Giant Molecular Clouds (GMCs) for star formation. We introduce the Astro-DSB model, a variant of DSB with the pairwise domain as…

• Rethinking generative image pretraining: How far are we from scaling up next-pixel prediction?

  Xinchen Yan, Chen Liang, Lijun Yu, Adams Wei Yu, Yifeng Lu, Quoc V. Le · 13 November 2025

  This paper investigates the scaling properties of autoregressive next-pixel prediction, a simple, end-to-end yet under-explored framework for unified vision models. Starting with images at resolutions of 32x32, we train a family of Transformers using IsoFlops profiles across compute budgets up to 7e…

• Improving Conditional VAE with approximation using Normalizing Flows

  Tuhin Subhra De · 13 November 2025

  Variational Autoencoders and Generative Adversarial Networks remained the state-of-the-art (SOTA) generative models until 2022. Now they are superseded by diffusion based models. Efforts to improve traditional models have stagnated as a result. In old-school fashion, we explore image generation with…

• Multi-step Predictive Coding Leads To Simplicity Bias

  Aviv Ratzon, Omri Barak · 13 November 2025

  Predictive coding is a framework for understanding the formation of low-dimensional internal representations mirroring the environment's latent structure. The conditions under which such representations emerge remain unclear. In this work, we investigate how the prediction horizon and network depth …

• Edit Flows: Flow Matching with Edit Operations

  Marton Havasi, Brian Karrer, Itai Gat, Ricky T. Q. Chen · 13 November 2025

  Autoregressive generative models naturally generate variable-length sequences, while non-autoregressive models struggle, often imposing rigid, token-wise structures. We propose Edit Flows, a non-autoregressive model that overcomes these limitations by defining a discrete flow over sequences through …

• PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

  PAN Team, Jiannan Xiang, Yi Gu, Zihan Liu, Zeyu Feng, Qiyue Gao, Yiyan Hu, Benhao Huang, Guangyi Liu, Yichi Yang, Kun Zhou, Davit Abrahamyan, Arif Ahmad, Ganesh Bannur, Junrong Chen, Kimi Chen, Mingkai Deng, Ruobing Han, Xinqi Huang, Haoqiang Kang, Zheqi Li, Enze Ma, Hector Ren, Yashowardhan Shinde, Rohan Shingre, Ramsundar Tanikella, Kaiming Tao, Dequan Yang, Xinle Yu, Cong Zeng, Binglin Zhou, Hector Liu, Zhiting Hu, Eric P. Xing · 13 November 2025

  A world model enables an intelligent agent to imagine, predict, and reason about how the world evolves in response to its actions, and accordingly to plan and strategize. While recent video generation models produce realistic visual sequences, they typically operate in the prompt-to-full-video manne…

• Multivariate Variational Autoencoder

  Mehmet Can Yavuz · 12 November 2025

  We present the Multivariate Variational Autoencoder (MVAE), a VAE variant that preserves Gaussian tractability while lifting the diagonal posterior restriction. MVAE factorizes each posterior covariance, where a \emph{global} coupling matrix $\mathbf{C}$ induces dataset-wide latent correlations and …

• Rectified Noise: A Generative Model Using Positive-incentive Noise

  Zhenyu Gu, Yanchen Xu, Sida Huang, Yubin Guo, Hongyuan Zhang · 12 November 2025

  Rectified Flow (RF) has been widely used as an effective generative model. Although RF is primarily based on probability flow Ordinary Differential Equations (ODE), recent studies have shown that injecting noise through reverse-time Stochastic Differential Equations (SDE) for sampling can achieve su…

• NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization

  Xiyuan Wei, Chih-Jen Lin, Tianbao Yang · 12 November 2025

  Accurately estimating the normalization term (also known as the partition function) in the contrastive loss is a central challenge for training Contrastive Language-Image Pre-training (CLIP) models. Conventional methods rely on large batches for approximation, demanding substantial computational res…

• HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization

  Zeyang Li, Kaveh Alim, Navid Azizan · 12 November 2025

  Diffusion and flow-matching have emerged as powerful methodologies for generative modeling, with remarkable success in capturing complex data distributions and enabling flexible guidance at inference time. Many downstream applications, however, demand enforcing hard constraints on generated samples …

• Concentration bounds on response-based vector embeddings of black-box generative models

  Aranyak Acharyya, Joshua Agterberg, Youngser Park, Carey E. Priebe · 12 November 2025

  Generative models, such as large language models or text-to-image diffusion models, can generate relevant responses to user-given queries. Response-based vector embeddings of generative models facilitate statistical analysis and inference on a given collection of black-box generative models. The Dat…

• Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective

  Justin Lee, Zheda Mai, Jinsu Yoo, Chongyu Fan, Cheng Zhang, Wei-Lun Chao · 12 November 2025

  Machine unlearning--the ability to remove designated concepts from a pre-trained model--has advanced rapidly, particularly for text-to-image diffusion models. However, existing methods typically assume that unlearning requests arrive all at once, whereas in practice they often arrive sequentially. W…

• Towards Synthesizing High-Dimensional Tabular Data with Limited Samples

  Zuqing Li, Junhao Gan, Jianzhong Qi · 12 November 2025

  Diffusion-based tabular data synthesis models have yielded promising results. However, when the data dimensionality increases, existing models tend to degenerate and may perform even worse than simpler, non-diffusion-based models. This is because limited training samples in high-dimensional space of…

• Accelerating Visual-Policy Learning through Parallel Differentiable Simulation

  Haoxiang You, Yilang Liu, Ian Abraham · 12 November 2025

  In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation graph, enabling seamless integration with existing differen…

• Rethinking Losses for Diffusion Bridge Samplers

  Sebastian Sanokowski, Lukas Gruber, Christoph Bartmann, Sepp Hochreiter, Sebastian Lehner · 12 November 2025

  Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outperforms the reverse Kullback-Leibler (rKL) loss when using the reparametrization trick to compute rKL-gradients. While the…