Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Synthetic Craquelure Generation for Unsupervised Painting Restoration

  Jana Cuch-Guill\'en, Antonio Agudo, Ra\"ul P\'erez-Gonzalo · 16. Februar 2026

  Cultural heritage preservation increasingly demands non-invasive digital methods for painting restoration, yet identifying and restoring fine craquelure patterns from complex brushstrokes remains challenging due to scarce pixel-level annotations. We propose a fully annotation-free framework driven b…

• Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures

  Luigi Fogliani, Bruno Loureiro, Marylou Gabri\'e · 16. Februar 2026

  Mode collapse, the failure to capture one or more modes when targetting a multimodal distribution, is a central challenge in modern variational inference. In this work, we provide a mathematical analysis of annealing based strategies for mitigating mode collapse in a tractable setting: learning a Ga…

• Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps

  Sangwoo Jo, Sungjoon Choi · 16. Februar 2026

  Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs. While prior work focuses on training objectives or individual solvers, the holistic design of sampling, specifically solver selection…

• Watermarking Discrete Diffusion Language Models

  Avi Bagchi, Akhil Bhimaraju, Moulik Choraria, Daniel Alabi, Lav R. Varshney · 16. Februar 2026

  Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image diffusion models, it remains comparatively underexplored fo…

• OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

  Maomao Li, Zhen Li, Kaipeng Zhang, Guosheng Yin, Zhifeng Li, Dong Xu · 16. Februar 2026

  Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts. Benefiting from the rapid advancement of joint audio-video generation, this paper proposes a more compelling new task: sync audio-video customization, w…

• Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation

  Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Nicu Sebe, Mubarak Shah · 16. Februar 2026

  Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain preferences is more difficult than learning other preferences, renderi…

• Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification

  Yuhao Sun, Jiacheng Zhang, Zesheng Ye, Chaowei Xiao, Feng Liu · 16. Februar 2026

  Diffusion-based purification (DBP) methods aim to remove adversarial noise from the input sample by first injecting Gaussian noise through a forward diffusion process, and then recovering the clean example through a reverse generative process. In the above process, how much Gaussian noise is injecte…

• Diverging Flows: Detecting Extrapolations in Conditional Generation

  Constantinos Tsakonas, Serena Ivaldi, Jean-Baptiste Mouret · 16. Februar 2026

  The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered by a critical extrapolation hazard: driven by smoothness bia…

• TFTF: Training-Free Targeted Flow for Conditional Sampling

  Qianqian Qu, Jun S. Liu · 16. Februar 2026

  We propose a training-free conditional sampling method for flow matching models based on importance sampling. Because a na\"ive application of importance sampling suffers from weight degeneracy in high-dimensional settings, we modify and incorporate a resampling technique in sequential Monte Carlo (…

• DistillKac: Few-Step Image Generation via Damped Wave Equations

  Weiqiao Han, Chenlin Meng, Christopher D. Manning, Stefano Ermon · 13. Februar 2026

  We present DistillKac, a fast image generator that uses the damped wave equation and its stochastic Kac representation to move probability mass at finite speed. In contrast to diffusion models whose reverse time velocities can become stiff and implicitly allow unbounded propagation speed, Kac dynami…

• General and Efficient Steering of Unconditional Diffusion

  Qingsong Wang, Mikhail Belkin, Yusu Wang · 13. Februar 2026

  Guiding unconditional diffusion models typically requires either retraining with conditional inputs or per-step gradient computations (e.g., classifier-based guidance), both of which incur substantial computational overhead. We present a general recipe for efficiently steering unconditional diffusio…

• SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities

  Dung Thuy Nguyen, Quang Nguyen, Preston K. Robinette, Eli Jiang, Taylor T. Johnson, Kevin Leach · 13. Februar 2026

  Recent advances in 3D-aware generative models have enabled high-fidelity image synthesis of human identities. However, this progress raises urgent questions around user consent and the ability to remove specific individuals from a model's output space. We address this by introducing SUGAR, a framewo…

• Exploring Multiple High-Scoring Subspaces in Generative Flow Networks

  Xuan Yu, Xu Wang, Rui Zhu, Yudong Zhang, Yang Wang · 13. Februar 2026

  As a probabilistic sampling framework, Generative Flow Networks (GFlowNets) show strong potential for constructing complex combinatorial objects through the sequential composition of elementary components. However, existing GFlowNets often suffer from excessive exploration over vast state spaces, le…

• Note on Martingale Theory and Applications

  Xiandong Zou · 13. Februar 2026

  This note investigates core properties of martingales, emphasizing the measure-theoretic formulation of conditional expectation, the martingale transform, and the upcrossing lemma. These results lead to the Martingale Convergence Theorem, which we then apply to study the extinction behavior in Galto…

• Adaptive Physics Transformer with Fused Global-Local Attention for Subsurface Energy Systems

  Xin Ju (Hadrian), Nok Hei (Hadrian), Fung, Yuyan Zhang, Carl Jacquemyn, Matthew Jackson, Randolph Settgast, Sally M. Benson, Gege Wen · 13. Februar 2026

  The Earth's subsurface is a cornerstone of modern society, providing essential energy resources like hydrocarbons, geothermal, and minerals while serving as the primary reservoir for $CO_2$ sequestration. However, full physics numerical simulations of these systems are notoriously computationally ex…

• DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

  Dianyi Wang, Ruihang Li, Feng Han, Chaofan Ma, Wei Song, Siyuan Wang, Yibin Wang, Yi Xin, Hongjian Liu, Zhixiong Zhang, Shengyuan Ding, Tianhang Wang, Zhenglin Cheng, Tao Lin, Cheng Jin, Kaicheng Yu, Jingjing Chen, Wenjie Wang, Zhongyu Wei, Jiaqi Wang · 13. Februar 2026

  Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight 5B unified model that achieves comprehensive capabilities co…

• Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation

  Alan Baade, Eric Ryan Chan, Kyle Sargent, Changan Chen, Justin Johnson, Ehsan Adeli, Li Fei-Fei · 13. Februar 2026

  Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling. They discard information during image encoding, require a separately trained decoder, and model an auxiliary distribution to the raw data. In this paper, we propose Latent Forcing, a simple …

• Learn from Your Mistakes: Self-Correcting Masked Diffusion Models

  Yair Schiff, Omer Belhasin, Roy Uziel, Guanghan Wang, Marianne Arriola, Gilad Turok, Michael Elad, Volodymyr Kuleshov · 13. Februar 2026

  Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models, enabling parallel token generation while achieving competitive performance. Despite these advantages, MDMs face a fundamental limitation: once tokens are unmasked, they remain fixed, leading to error acc…

• MonarchRT: Efficient Attention for Real-Time Video Generation

  Krish Agarwal, Zhuoming Chen, Cheng Luo, Yongqi Chen, Haizhong Zheng, Xun Huang, Atri Rudra, Beidi Chen · 13. Februar 2026

  Real-time video generation with Diffusion Transformers is bottlenecked by the quadratic cost of 3D self-attention, especially in real-time regimes that are both few-step and autoregressive, where errors compound across time and each denoising step must carry substantially more information. In this s…

• Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning

  Xuan Yu, Xu Wang, Rui Zhu, Yudong Zhang, Yang Wang · 13. Februar 2026

  Generative Flow Networks (GFlowNets) have shown promising potential to generate high-scoring candidates with probability proportional to their rewards. As existing GFlowNets freely explore in state space, they encounter significant convergence challenges when scaling to large state spaces. Addressin…

• PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models

  Jiangong Chen, Mingyu Zhu, Bin Li · 12. Februar 2026

  Multimodal Large Language Models (MLLMs) enhance collaboration in Extended Reality (XR) environments by enabling flexible object and animation creation through the combination of natural language and visual inputs. However, visual data captured by XR headsets includes real-world backgrounds that may…

• Coarse-Grained Boltzmann Generators

  Weilong Chen, Bojun Zhao, Jan Eckwert, Julija Zavadlav · 12. Februar 2026

  Sampling equilibrium molecular configurations from the Boltzmann distribution is a longstanding challenge. Boltzmann Generators (BGs) address this by combining exact-likelihood generative models with importance sampling, but their practical scalability is limited. Meanwhile, coarse-grained surrogate…

• Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance

  Jacob L. Block, Mehryar Mohri, Aryan Mokhtari, Sanjay Shakkottai · 12. Februar 2026

  We study machine unlearning in large generative models by framing the task as density ratio estimation to a target distribution rather than supervised fine-tuning. While classifier guidance is a standard approach for approximating this ratio and can succeed in general, we show it can fail to faithfu…

• Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling

  Gongye Liu, Bo Yang, Yida Zhi, Zhizhou Zhong, Lei Ke, Didan Deng, Han Gao, Yongxiang Huang, Kaihao Zhang, Hongbo Fu, Wenhan Luo · 12. Februar 2026

  Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider, leveraging their rich multimodal priors to guide alignment. Howeve…

• ELROND: Exploring and decomposing intrinsic capabilities of diffusion models

  Pawe{\l} Skier\'s, Tomasz Trzci\'nski, Kamil Deja · 12. Februar 2026

  A single text prompt passed to a diffusion model often yields a wide range of visual outputs determined solely by stochastic process, leaving users with no direct control over which specific semantic variations appear in the image. While existing unsupervised methods attempt to analyze these variati…