Generative Adversarial Networks and Image Synthesis

Latest papers

• ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Consistent Attention

  Huiguo He, Pengyu Yan, Ziqi Yi, Weizhi Zhong, Zheng Liu, Yejun Tang, Huan Yang, Kun Gai, Guanbin Li, Lianwen Jin · 10 December 2025

  Drag-based image editing aims to modify visual content followed by user-specified drag operations. Despite existing methods having made notable progress, they still fail to fully exploit the contextual information in the reference image, including fine-grained texture details, leading to edits with …

• Astra: General Interactive World Model with Autoregressive Denoising

  Yixuan Zhu, Jiaqi Feng, Wenzhao Zheng, Yuan Gao, Xin Tao, Pengfei Wan, Jie Zhou, Jiwen Lu · 10 December 2025

  Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and actions remain underexplored, especially for general-purpose s…

• Discovering Influential Factors in Variational Autoencoders

  Shiqi Liu, Jingxin Liu, Qian Zhao, Xiangyong Cao, Huibin Li, Deyu Meng, Hongying Meng, Sheng Liu · 10 December 2025

  In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extrac…

• TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

  Zheng Ding, Weirui Ye · 10 December 2025

  Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption. We introduce \textbf{TreeGRPO}, a novel RL framework that dramatically improves training efficiency by re…

• SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

  Yanxu Meng, Haoning Wu, Ya Zhang, Weidi Xie · 10 December 2025

  3D content generation has recently attracted significant research interest, driven by its critical applications in VR/AR and embodied AI. In this work, we tackle the challenging task of synthesizing multiple 3D assets within a single scene image. Concretely, our contributions are fourfold: (i) we pr…

• Generation is Required for Data-Efficient Perception

  Jack Brady, Bernhard Sch\"olkopf, Thomas Kipf, Simon Buchholz, Wieland Brendel · 10 December 2025

  It has been hypothesized that human-level visual perception requires a generative approach in which internal representations result from inverting a decoder. Yet today's most successful vision models are non-generative, relying on an encoder that maps images to representations without decoder invers…

• A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation

  Zhigang Jia, Duan Wang, Hengkai Wang, Yajun Xie, Meixiang Zhao, Xiaoyu Zhao · 10 December 2025

  Color image generation has a wide range of applications, but the existing generation models ignore the correlation among color channels, which may lead to chromatic aberration problems. In addition, the data distribution problem of color images has not been systematically elaborated and explained, s…

• Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps

  Seoyeon Lee, Gwangyeol Yu, Chaewon Kim, Jonghyuk Park · 10 December 2025

  Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation quality by detecting these flaws. The framework employs an ex…

• Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

  Boheng Li, Renjie Gu, Junjie Wang, Leyi Qi, Yiming Li, Run Wang, Zhan Qin, Tianwei Zhang · 9 December 2025

  Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications. However, these models often inherit unsafe behaviors from toxic pretraining data, raising growing safety concerns. While recent safety-driven unlearni…

• Winning the Lottery by Preserving Network Training Dynamics with Concrete Ticket Search

  Tanay Arora, Christof Teuscher · 9 December 2025

  The Lottery Ticket Hypothesis asserts the existence of highly sparse, trainable subnetworks ('winning tickets') within dense, randomly initialized neural networks. However, state-of-the-art methods of drawing these tickets, like Lottery Ticket Rewinding (LTR), are computationally prohibitive, while …

• Density Operator Expectation Maximization

  Adit Vishnu, Abhay Shastry, Dhruva Kashyap, Chiranjib Bhattacharyya · 9 December 2025

  Machine learning with density operators, the mathematical foundation of quantum mechanics, is gaining prominence with rapid advances in quantum computing. Generative models based on density operators cannot yet handle tasks that are routinely handled by probabilistic models. The progress of latent v…

• Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity

  Noa Rubin, Orit Davidovich, Zohar Ringel · 9 December 2025

  Two pressing topics in the theory of deep learning are the interpretation of feature learning mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich feature learning, often appear in the form of high-dimensional non-linear equations, which require …

• Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces

  Nikita Gabdullin · 9 December 2025

  The overall neural network (NN) performance is closely related to the properties of its embedding distribution in latent space (LS). It has recently been shown that predefined vector systems, specifically An root system vectors, can be used as targets for latent space configurations (LSC) to ensure …

• Fast training and sampling of Restricted Boltzmann Machines

  Nicolas B\'ereux, Aur\'elien Decelle, Cyril Furtlehner, Lorenzo Rosset, Beatriz Seoane · 9 December 2025

  Restricted Boltzmann Machines (RBMs) are powerful tools for modeling complex systems and extracting insights from data, but their training is hindered by the slow mixing of Markov Chain Monte Carlo (MCMC) processes, especially with highly structured datasets. In this study, we build on recent theore…

• GatedFWA: Linear Flash Windowed Attention with Gated Associative Memory

  Jiaxu Liu, Yuhe Bai, Christos-Savvas Bouganis · 9 December 2025

  Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention pattern, but under an \textit{Associative Memory} interpretati…

• Generative Machine Learning for Multivariate Angular Simulation

  Jakob Benjamin Wessel, Callum J. R. Murphy-Barltrop, Emma S. Simpson · 9 December 2025

  With the recent development of new geometric and angular-radial frameworks for multivariate extremes, reliably simulating from angular variables in moderate-to-high dimensions is of increasing importance. Empirical approaches have the benefit of simplicity, and work reasonably well in low dimensions…

• Rethinking Training Dynamics in Scale-wise Autoregressive Generation

  Gengze Zhou, Chongjian Ge, Hao Tan, Feng Liu, Yicong Hong · 9 December 2025

  Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine manner. However, scale-wise AR models suffer from exposure b…

• Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions

  Kaichen Shen, Wei Zhu · 9 December 2025

  We present latent nonlinear denoising score matching (LNDSM), a novel training objective for score-based generative models that integrates nonlinear forward dynamics with the VAE-based latent SGM framework. This combination is achieved by reformulating the cross-entropy term using the approximate Ga…

• Optimal and Diffusion Transports in Machine Learning

  Gabriel Peyr\'e · 9 December 2025

  Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This includes sampling via diffusion methods, optimizing the weights of neural networks, and analyzing the evolution of token distributions across layers of large langu…

• Formalized Hopfield Networks and Boltzmann Machines

  Matteo Cipollina, Michail Karatarakis, Freek Wiedijk · 9 December 2025

  Neural networks are widely used, yet their analysis and verification remain challenging. In this work, we present a Lean 4 formalization of neural networks, covering both deterministic and stochastic models. We first formalize Hopfield networks, recurrent networks that store patterns as stable state…

• Towards Robust Protective Perturbation against DeepFake Face Swapping

  Hengyang Yao, Lin Li, Ke Sun, Jianing Qiu, Huiping Chen · 9 December 2025

  DeepFake face swapping enables highly realistic identity forgeries, posing serious privacy and security risks. A common defence embeds invisible perturbations into images, but these are fragile and often destroyed by basic transformations such as compression or resizing. In this paper, we first cond…

• FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers

  Jonghyun Park, Jong Chul Ye · 9 December 2025

  Deep generative models have become powerful priors for solving inverse problems, and various training-free methods have been developed. However, when applied to latent flow models, existing methods often fail to converge to the posterior mode or suffer from manifold deviation within latent spaces. T…

• Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation

  Xingyang Li, Muyang Li, Tianle Cai, Haocheng Xi, Shuo Yang, Yujun Lin, Lvmin Zhang, Songlin Yang, Jinbo Hu, Kelly Peng, Maneesh Agrawala, Ion Stoica, Kurt Keutzer, Song Han · 9 December 2025

  Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this paper, we identify a phenomenon we term Spatiotemporal Ener…

• World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty

  Zhiting Mei, Tenny Yin, Micah Baker, Ola Shorinwa, Anirudha Majumdar · 9 December 2025

  Recent advances in generative video models have led to significant breakthroughs in high-fidelity video synthesis, specifically in controllable video generation where the generated video is conditioned on text and action inputs, e.g., in instruction-guided video editing and world modeling in robotic…

• NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation

  Yu Zeng, Charles Ochoa, Mingyuan Zhou, Vishal M. Patel, Vitor Guizilini, Rowan McAllister · 9 December 2025

  Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image generation, corrupting phase components destroys spatial structure, making it ill-suited for tasks requiring geometric consist…