Generative Adversarial Networks and Image Synthesis

Neueste Paper

• CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature

  Eldad Matmon, Amit Bracha, Noam Rotstein, Ron Kimmel · 8. Januar 2026

  A photorealistic and controllable 3D caricaturization framework for faces is introduced. We start with an intrinsic Gaussian curvature-based surface exaggeration technique, which, when coupled with texture, tends to produce over-smoothed renders. To address this, we resort to 3D Gaussian Splatting (…

• Logic Tensor Network-Enhanced Generative Adversarial Network

  Nijesh Upreti (The University of Edinburgh), Vaishak Belle (The University of Edinburgh) · 8. Januar 2026

  In this paper, we introduce Logic Tensor Network-Enhanced Generative Adversarial Network (LTN-GAN), a novel framework that enhances Generative Adversarial Networks (GANs) by incorporating Logic Tensor Networks (LTNs) to enforce domain-specific logical constraints during the sample generation process…

• LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing

  Wingwa Fu, Takayuki Okatani · 7. Januar 2026

  Text-to-Image editing using diffusion models faces challenges in balancing content preservation with edit application and handling real-image editing. To address these, we propose LAMS-Edit, leveraging intermediate states from the inversion process--an essential step in real-image editing--during ed…

• Unified Thinker: A General Reasoning Modular Core for Image Generation

  Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao · 7. Januar 2026

  Despite impressive progress in high-fidelity image synthesis, generative models still struggle with logic-intensive instruction following, exposing a persistent reasoning--execution gap. Meanwhile, closed-source systems (e.g., Nano Banana) have demonstrated strong reasoning-driven image generation, …

• Learning to Act Robustly with View-Invariant Latent Actions

  Youngjoon Jeong, Junha Chun, Taesup Kim · 7. Januar 2026

  Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronounced in real-world settings, where viewpoint variability is unavoidable and can significantly disrupt policy performance.…

• DreamLoop: Controllable Cinemagraph Generation from a Single Photograph

  Aniruddha Mahapatra, Long Mai, Cusuh Ham, Feng Liu · 7. Januar 2026

  Cinemagraphs, which combine static photographs with selective, looping motion, offer unique artistic appeal. Generating them from a single photograph in a controllable manner is particularly challenging. Existing image-animation techniques are restricted to simple, low-frequency motions and operate …

• Critic-Guided Reinforcement Unlearning in Text-to-Image Diffusion

  Mykola Vysotskyi, Zahar Kohut, Mariia Shpir, Taras Rumezhak, Volodymyr Karpiv · 7. Januar 2026

  Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically rely on supervised weight edits or global penalties; reinforcement-learning (RL) approaches, while flexible, often optimize sparse end-…

• Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning

  Yuankun Xie, Xiaoxuan Guo, Jiayi Zhou, Tao Wang, Jian Liu, Ruibo Fu, Xiaopeng Wang, Haonan Cheng, Long Ye · 7. Januar 2026

  Recent advances in audio large language models (ALLMs) have made high-quality synthetic audio widely accessible, increasing the risk of malicious audio deepfakes across speech, environmental sounds, singing voice, and music. Real-world audio deepfake detection (ADD) therefore requires all-type detec…

• Stratified Hazard Sampling: Minimal-Variance Event Scheduling for CTMC/DTMC Discrete Diffusion and Flow Models

  Seunghwan Jang, SooJean Han · 7. Januar 2026

  CTMC/DTMC-based discrete generative models, including uniform-noise discrete diffusion (e.g., D3PM/CTDD) and discrete flow matching, enable non-autoregressive sequence generation by repeatedly replacing tokens through a time-inhomogeneous Markov process. Inference is typically implemented with step-…

• Annealed Langevin Posterior Sampling (ALPS): A Rapid Algorithm for Image Restoration with Multiscale Energy Models

  Jyothi Rikhab Chand, Mathews Jacob · 7. Januar 2026

  Solving inverse problems in imaging requires models that support efficient inference, uncertainty quantification, and principled probabilistic reasoning. Energy-Based Models (EBMs), with their interpretable energy landscapes and compositional structure, are well-suited for this task but have histori…

• PICABench: How Far Are We from Physically Realistic Image Editing?

  Yuandong Pu, Le Zhuo, Songhao Han, Jinbo Xing, Kaiwen Zhu, Shuo Cao, Bin Fu, Si Liu, Hongsheng Li, Yu Qiao, Wenlong Zhang, Xi Chen, Yihao Liu · 6. Januar 2026

  Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond completing the editing instructions, the accompanying physical effects are the key to the generation realism. For example, remo…

• NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

  Huichao Zhang, Liao Qu, Yiheng Liu, Hang Chen, Yangyang Song, Yongsheng Dong, Shikun Sun, Xian Li, Xu Wang, Yi Jiang, Hu Ye, Bo Chen, Yiming Gao, Peng Liu, Akide Liu, Zhipeng Yang, Qili Deng, Linjie Xing, Jiyang Liu, Zhao Wang, Yang Zhou, Mingcong Liu, Yi Zhang, Qian He, Xiwei Hu, Zhongqi Qi, Jie Shao, Zhiye Fu, Shuai Wang, Fangmin Chen, Xuezhi Chai, Zhihua Wu, Yitong Wang, Zehuan Yuan, Daniel K. Du, Xinglong Wu · 6. Januar 2026

  We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architecture, NextFlow natively activates multimodal understanding and generation capabil…

• AH-GS: Augmented 3D Gaussian Splatting for High-Frequency Detail Representation

  Chenyang Xu, XingGuo Deng, Rui Zhong · 6. Januar 2026

  The 3D Gaussian Splatting (3D-GS) is a novel method for scene representation and view synthesis. Although Scaffold-GS achieves higher quality real-time rendering compared to the original 3D-GS, its fine-grained rendering of the scene is extremely dependent on adequate viewing angles. The spectral bi…

• Spectral-Window Hybrid (SWH)

  Vladimer Khasia · 6. Januar 2026

  Scaling sequence modeling to extreme contexts requires balancing computational efficiency with representational expressivity. While Transformers provide precise retrieval via the attention mechanism, their quadratic $\mathcal{O}(T^2)$ complexity limits their application to long-horizon tasks. In thi…

• Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding

  Yixuan Lai, He Wang, Kun Zhou, Tianjia Shao · 6. Januar 2026

  Producing prompt-faithful videos that preserve a user-specified identity remains challenging: models need to extrapolate facial dynamics from sparse reference while balancing the tension between identity preservation and motion naturalness. Conditioning on a single image completely ignores the tempo…

• VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation

  Shikun Sun, Liao Qu, Huichao Zhang, Yiheng Liu, Yangyang Song, Xian Li, Xu Wang, Yi Jiang, Daniel K. Du, Xinglong Wu, Jia Jia · 6. Januar 2026

  Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates severe asynchronous policy conflicts. This issue becomes par…

• Coarse-Grained Kullback--Leibler Control of Diffusion-Based Generative AI

  Tatsuaki Tsuruyama · 6. Januar 2026

  Diffusion models and score-based generative models provide a powerful framework for synthesizing high-quality images from noise. However, there is still no satisfactory theory that describes how coarse-grained quantities, such as blockwise intensity or class proportions after partitioning an image i…

• Forget Less by Learning from Parents Through Hierarchical Relationships

  Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Nalini K. Ratha, Venu Govindaraju · 6. Januar 2026

  Custom Diffusion Models (CDMs) offer impressive capabilities for personalization in generative modeling, yet they remain vulnerable to catastrophic forgetting when learning new concepts sequentially. Existing approaches primarily focus on minimizing interference between concepts, often neglecting th…

• Length-Aware Adversarial Training for Variable-Length Trajectories: Digital Twins for Mall Shopper Paths

  He Sun, Jiwoong Shin, Ravi Dhar · 6. Januar 2026

  We study generative modeling of \emph{variable-length trajectories} -- sequences of visited locations/items with associated timestamps -- for downstream simulation and counterfactual analysis. A recurring practical issue is that standard mini-batch training can be unstable when trajectory lengths ar…

• Deep Clustering with Associative Memories

  Bishwajit Saha, Dmitry Krotov, Mohammed J. Zaki, Parikshit Ram · 6. Januar 2026

  Deep clustering - joint representation learning and latent space clustering - is a well studied problem especially in computer vision and text processing under the deep learning framework. While the representation learning is generally differentiable, clustering is an inherently discrete optimizatio…

• Agentic Retoucher for Text-To-Image Generation

  Shaocheng Shen, Jianfeng Liang. Chunlei Cai, Cong Geng, Huiyu Duan, Xiaoyun Zhang, Qiang Hu, Guangtao Zhai · 6. Januar 2026

  Text-to-image (T2I) diffusion models such as SDXL and FLUX have achieved impressive photorealism, yet small-scale distortions remain pervasive in limbs, face, text and so on. Existing refinement approaches either perform costly iterative re-generation or rely on vision-language models (VLMs) with we…

• Speak the Art: A Direct Speech to Image Generation Framework

  Mariam Saeed, Manar Amr, Farida Adel, Nada Hassan, Nour Walid, Eman Mohamed, Mohamed Hussein, Marwan Torki · 6. Januar 2026

  Direct speech-to-image generation has recently shown promising results. However, compared to text-to-image generation, there is still a large gap to enclose. Current approaches use two stages to tackle this task: speech encoding network and image generative adversarial network (GAN). The speech enco…

• Geometric and Dynamic Scaling in Deep Transformers

  Haoran Su, Chenyu You · 6. Januar 2026

  Despite their empirical success, pushing Transformer architectures to extreme depth often leads to a paradoxical failure: representations become increasingly redundant, lose rank, and ultimately collapse. Existing explanations largely attribute this phenomenon to optimization instability or vanishin…

• Deep Linear Discriminant Analysis Revisited

  Maxat Tezekbayev, Rustem Takhanov, Arman Bolatov, Zhenisbek Assylbekov · 6. Januar 2026

  We show that for unconstrained Deep Linear Discriminant Analysis (LDA) classifiers, maximum-likelihood training admits pathological solutions in which class means drift together, covariances collapse, and the learned representation becomes almost non-discriminative. Conversely, cross-entropy trainin…

• Generative Conditional Missing Imputation Networks

  George Sun, Yi-Hui Zhou · 5. Januar 2026

  In this study, we introduce a sophisticated generative conditional strategy designed to impute missing values within datasets, an area of considerable importance in statistical analysis. Specifically, we initially elucidate the theoretical underpinnings of the Generative Conditional Missing Imputati…