Generative Adversarial Networks and Image Synthesis

Latest papers

• IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation

  Yiting Wang, Jingyi Zhang, Wenhu Zhang, Ke Chao, Yves Liang, Kun Cheng, Kang Zhao · 13 July 2026

  While large-scale text-to-image generative models have achieved unprecedented visual performance, their inherent reliance on multi-step iterative solvers incurs severe inference latency. Few-step distillation targeting the Classifier-Free Guidance (CFG) trajectory has emerged as the prevalent dual-d…

• CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation

  Seungyong Lee, Hyun Jun Jang, Sangoh Kim, Sungjoon Park · 13 July 2026

  Virtual try-on (VTO) has made significant progress in realistically transferring garments onto a target person. Yet most systems give the user little control over how a garment should be worn -- its size (loose or fitted), style (e.g., tucked in or untucked, open or closed), and spatial placement on…

• M4V: Multimodal Mamba for Efficient Text-to-Video Generation

  Jiancheng Huang, Gengwei Zhang, Zequn Jie, Siyu Jiao, Yinlong Qian, Ling Chen, Yunchao Wei, Lin Ma · 13 July 2026

  Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators. However, modeling the vast spatiotemporal space remains computationally demanding, particularly when employing Transformers, which incur quadratic complexity in sequ…

• ArtMine: Discovering and Formalizing Artistic Processes

  Kaustubh Kumar, Ashutosh Ranjan, Vivek Srivastava, Blessin Varkey, Shirish Karande · 10 July 2026

  Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production. While recent generative AI systems can synthesize artworks with high fidelity, they primarily model distributions over finished arti…

• CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation

  Sai Spandana Chintapalli, Pratik Chaudhari, Christos Davatzikos · 10 July 2026

  Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems (e.g., diseased vs. healthy). Yet, without paired data and in the presence of heterogeneous target variation, existing methods struggle to separate multiple modes of …

• An exact information theory of generalization phase transitions in Bayesian diffusion models

  Henry Hunt, Mason Kamb, Surya Ganguli · 10 July 2026

  How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introduce analytically tractable Bayesian information restricted diffusion …

• AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate

  Siyuan Wen, Jiahao Zeng, Ningning Ding · 10 July 2026

  Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models. Current diffusion unlearning techniques determine the model update direction by either using alternatives of the target concept as an anchor or using empty prompts. The anchor-b…

• JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators

  Ce Chen, Congrui Wang, Yonglin Li, Zhenchen Wan, Mingyang Geng, Junhao Xiao, Zhengpeng Xing, Yaqing Hu, Yao Wu, Zhaoyang Qu, Long Lan, Xinwang Liu, Yingqi Peng, Shijia Li, Zufeng Zhang, Chen Ma, Jingjing Zhou, Xingyu Wang, Qilin Lu, Bin Jiang, Qilin Sun, Shanzhi Gu, Yaoguang Jin, Tongliang Liu, Kede Ma, Yifan Peng · 9 July 2026

  Text-to-image (T2I) diffusion models typically require substantial computational resources and cloud infrastructure, posing significant challenges for edge deployment in terms of latency, cost, and user privacy. We present JuZhou 1.0, an ultra-lightweight T2I foundation model designed for fully offl…

• Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation

  Yu Cheng, Siyue Yao, Zhongang Qi, Shanyan Guan, Wei Li, Fajie Yuan · 9 July 2026

  Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significantly accelerate inference, they typically enforce a static model architecture across all denoising stages, ignoring the …

• Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery

  Chuyao Zhang, E Li, Taochen Chen, Yiqun Zhang, Yuzhu Ji, Shuping Zhao, Peng Liu, Yiu-ming Cheung · 9 July 2026

  Missing data is prevalent in practical applications, making effective imputation an essential preprocessing step for downstream analysis. Real-world datasets often exhibit complex latent structures composed of multiple subgroups with distinct distributions. However, existing methods often overlook s…

• Making Implicit Preservation Intent Explicit in Conversational Image Editing

  Soomin Han, Jihyung Ahn, Bumsoo Kim, Buru Chang · 9 July 2026

  Conversational image editing requires preserving not only visible content, but also content that temporarily disappears across turns. When newly added or modified content occludes a previously visible region, that region should reappear if it was never semantically changed. However, existing systems…

• The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?

  Donna Vakalis · 9 July 2026

  A learned world model is usually judged by how faithfully it reconstructs its observations or predicts reward, as though quality were something the model simply has or lacks. But what a task actually needs from a model is narrower: the few predictive coordinates its queries depend on, which we call …

• Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance

  Shiheng Zhang · 9 July 2026

  Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with more steps or limited-interval schedules. We analyze CFG through an asymptotic-pr…

• Heterogeneity-Adaptive Diffusion Schrodinger Bridge for PET-Guided Whole-Body MRI Translation

  Chengbo Wang, Jiacheng Yu, Linjie Bian, Ming Qi, Xiaosheng Liu, Tongtong Che, Jichang Zhang, Shuyu Li, Shaoli Song, Xiuying Wang · 9 July 2026

  While whole-body multimodal medical imaging scanners have been increasingly recognized for more effective medical applications, the excessive long acquisition time in PET-MR scanning is a major obstacle in more efficient clinical practice. Deep learning-based MRI translation provides a potential sol…

• AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis

  Humasak Tommy Argo Simanjuntak, Jesika Purba, Sitogab Girsang, Widya Manurung, Samuel Situmeang, Arlinta Barus, Daniel Oranova Siahaan · 9 July 2026

  Preserving and revitalising traditional textiles such as Ulos, a cultural heritage of the Batak ethnic group in North Sumatra, Indonesia, requires balancing fidelity to tradition with innovative approaches that meet contemporary design demands. Traditional Ulos weaving faces two key limitations: a n…

• D2PO: Optimizing Diffusion Samplers via Dynamic Preference

  Jinkyu Kim, Jinyoung Choi, Bohyung Han · 9 July 2026

  We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with respect to timestep schedules and classifier-free guidance (CFG) weights. Our work is motivated by a fundamental limitation of existing student-teacher regression framewor…

• UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks

  Yifan Zhang, Yuxin Hu, Zhuobin Hao, Xiaozhuan Gao, Lipeng Pan · 9 July 2026

  Self-paced learning (SPL) is an effective learning paradigm that simulates the human learning process by progressing from easy to difficult samples based on the value of the loss function during the learning process. It has shown great potential in improving model performance and training efficiency…

• An Hybrid Quantum-Classical Diffusion Model for Image Generation

  Qipeng Qian, Keli Deng, Yuntao Qian · 9 July 2026

  Quantum diffusion models provide a physics-consistent route to generative learning by formulating noising and denoising directly on quantum states. However, applying such models to classical high-dimensional data is constrained by the qubit cost of state encoding and the computational burden of simu…

• Gen4U: Unifying Video Generation and Understanding via Diffusion

  Michael King, Aravindh Mahendran, Matthew Koichi Grimes, Fedor Kitashov, Adham Elarabawy, Pedro Velez, Maks Ovsjanikov, Viorica P\u{a}tr\u{a}ucean · 9 July 2026

  Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models overcome this limitation. By systematically probing their intermediate activations using recent mutual-kNN alignment metri…

• VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection

  Sharayu N. Deshmukh, Md Rashidunnabi, Nelton Tiago Gemo, Kurundkar G. D., Mahamune M. R., Nilesh K. Deshmukh · 8 July 2026

  Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. Despite their widespread use, these paradigms are rarely evaluated under a common protocol, making direct comparison difficult…

• Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers

  Evelyn Turri, Davide Bucciarelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia · 8 July 2026

  Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood. In this work, we study massive activations: a small subset of hidden-state channe…

• $\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse

  Girum Demisse · 8 July 2026

  Variational Autoencoders (VAEs) frequently suffer from posterior collapse, a failure mode in which the approximate posterior converges to the prior, rendering the latent code uninformative. Despite extensive research, a unified account of why collapse occurs has remained an open question. We identif…

• Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization

  Xin Ding, Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang · 8 July 2026

  Recent advances in continuous conditional generative modeling, including Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM), estimate high-dimensional data distributions conditioned on scalar regression labels such as angles, ages, or temp…

• A Constrained Optimization Perspective of Unrolled Transformers

  Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro · 8 July 2026

  We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints on the objective function and replace standard empirical risk minimization (ERM) with a primal-dual training scheme. Th…

• Orthogonal Dendritic Intrinsic Networks: An Architecture for Significance-Ordered, Orthogonal Latent Spaces

  Jeanie Schreiber, Tyrus Berry, Zeeshan Ahmed · 8 July 2026

  Principal Component Analysis or PCA-like properties (orthogonality, variance ranking) are seldom realized in deep autoencoder architectures. In this work, we present ODIN (Orthogonal Dendritic Intrinsic Network), a novel autoencoder architecture that recovers PCA-like latent structure in a fully non…