Generative Adversarial Networks and Image Synthesis

Últimos artículos

• DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learning

  Tharindu Fernando, Clinton Fookes, Sridha Sridharan · 7 de agosto de 2026

  Rapid advances in generative AI have led to increasingly realistic deepfakes, posing growing challenges for law enforcement and public trust. Existing passive deepfake detectors struggle to keep pace, largely due to their dependence on specific forgery artifacts, which limits their ability to genera…

• In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion

  Lingxiao Yang, Liu Liu, Moran Li, Han Feng, Wenjian Cao, Jiangning Zhang, Ye Shi · 7 de agosto de 2026

  Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean frames leak excessive local details, which causes the model to take shortcuts, resulting in compromised temporal semanti…

• KVAE: Family of Tokenizers for Multimodal Generative Models

  Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov, Kirill Chernyshev, Kirill Malakhov, Ilia Vasiliev, Ilia Trushkin, Valeriya Kobenko, David Chikovani, Alexander Ivanov, Azat Saginbaev, Egor Silvestrov, Ivan Mikheev, Konstantin Zakharov · 7 de agosto de 2026

  Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for la…

• UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on

  Yushe Cao, Shikun Feng, Fei Shen, Haikuo Peng, Jianqiang Xia, Yiheng Zhu, Dianxi Shi, Chun Yu · 7 de agosto de 2026

  Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics. Dominant approaches cast VVT as mask-conditioned video inpainting and rely on separate modules for human parsing, pose estimation, and garment warping. This mult…

• PRISM: Distribution-Gated Flow Matching for Controllable Unpaired Image Translation

  Elad Yoshai, Natan T. Shaked · 7 de agosto de 2026

  Unpaired image-to-image translation must decide, per image, what to change and what to preserve without paired supervision. Many diffusion-based unpaired translators control preservation through a single global noise or guidance value applied across the image, which cannot separate content to keep f…

• Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models

  Duong Bach, Hai Nguyen Hong, Cuong Do · 7 de agosto de 2026

  Factorized generative models commonly regularize a latent style variable z_s by matching its marginal distribution to a fixed Gaussian prior and interpret this as evidence that the style representation is independent of class information. We show that this interpretation is incorrect. Matching only …

• A Reverse-BSDE Diffusion Sampler

  Jairon H. N. Batista, Fl\'avio B. Gon\c{c}alves, Yuri F. Saporito, Rodrigo S. Targino · 7 de agosto de 2026

  Diffusion-based generative models have renewed interest in stochastic differential equation methods for sampling from complex distributions. We study a setting in which the target density is known only up to a normalizing constant and reformulate the reverse-time diffusion sampler as a forward-backw…

• Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds

  Yizhu Wang, Mu Niu, Xiaochen Yang · 6 de agosto de 2026

  We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds. While diffusion models (DMs) have achieved state-of-the-art results in high-dimensional data synthesis, t…

• NuclearDiffusion: Text-to-Image Foundation Models for Learning Nuclear Energy Concepts

  Mohammed I. Radaideh, Jeremy Moon, Andre Gala-Garza, Emma Son, Yug Shah, Majdi I. Radaideh · 6 de agosto de 2026

  Generative artificial intelligence (AI) has transformed text-to-image synthesis, yet its ability to represent specialized engineering domains remains largely unexplored. As an exmaple in nuclear engineering, general-purpose foundation models frequently generate physically incorrect or conceptually i…

• When does training on downscaled images yield the same gradients?

  Seunghyun Ji · 6 de agosto de 2026

  Diffusion transformers deliver strong image generation, but their training cost grows superlinearly with resolution. Recent work justifies training or sampling at reduced resolution on a spectral premise: at high noise, a downscaled latent preserves almost the full surviving signal. Whether a downsc…

• CSGen: A Multi-Domain Curvilinear Structure Generation Model via Hierarchical Multimodal Diffusion

  Zhe Shan, Ziming Yang, Lei Zhou, Wenwen Zhang, Cong Lin, Xia Xie · 6 de agosto de 2026

  Curvilinear structure analysis is an important and fundamental task in multimedia. However, the controllable generation of images with precise curvilinear structure objects remains an open challenge. To address this, we propose CSGen, a hierarchical multimodal diffusion model that synthesizes high-f…

• Latent Reward Registers for Diffusion Preference Alignment

  Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun · 5 de agosto de 2026

  Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process. We propose Latent Reward Registers, a mechanism that estimates termi…

• Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

  Siming Fu, Zheming Fu, Ruizhe He, Hualiang Wang, Jie Huang, Xiaoxiao Ma, Mingchen Zhong, Weihu Huang, Xiaoxuan He, Haojun Xu · 5 de agosto de 2026

  On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teache…

• WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model

  Leyang Chen, Junyi Wu, Shaoqiu Zhang, Yulun Zhang · 4 de agosto de 2026

  Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse intermediate features, selectively update tokens, or reuse and extrapolate denoising outputs ac- cording to local drift or short native-space historie…

• SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching

  Zong-Wei Hong, Jinglun Li, Shen Zhang, Yuhan Liu, Linze Li, Yao Tang · 4 de agosto de 2026

  Denoising diffusion transformers achieve strong generation quality but converge slowly during training. Regularizing their internal representations has emerged as an effective accelerator, yet existing methods split into two families with complementary costs. Target-based methods strengthen represen…

• Face-D(^2)CL: Multi-Domain Synergistic Representation with Dual Continual Learning for Facial DeepFake Detection

  Yushuo Zhang, Yu Cheng, Yongkang Hu, Jiuan Zhou, Jiawei Chen, Zhaoxia Yin · 4 de agosto de 2026

  Facial forgery techniques are advancing rapidly, posing severe threats to public trust and information security while imposing higher demands on the continual adaptation of DeepFake detection models. Although continual learning enables models to adapt to emerging forgery methods, existing approaches…

• Beckmann Transport Models: From Autonomous Flows to One-Step Maps

  Lee Cheuk-Kit, Florentin Coeurdoux, Peter Potaptchik, Yilun Du, Michael Samuel Albergo, Eric Vanden-Eijnden · 4 de agosto de 2026

  We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the target is singular, i.e.\ supported on a lower-dimensional data manifold. We also show that the one-step generative map a…

• One-Sided Quantile Coupling for Flow Matching

  Jin-Young Kim, So-Yoon Cho, Hyun-Gyoon Kim · 4 de agosto de 2026

  Flow Matching trains continuous-time generative models by regressing the velocity field of a probability path between a simple source distribution and a target data distribution. The coupling that pairs source and target samples strongly affects optimization and sample quality, but structured coupli…

• UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction

  Junno Yun, Ya\c{s}ar Utku Al\c{c}alar, Mehmet Ak\c{c}akaya · 4 de agosto de 2026

  Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks. DiTs comprise isotropic transformer blocks, and learn representations progressively across depth, where the denoising objective drives later layers …

• DiffusionGemma Technical Report

  DiffusionGemma Team, Adrien Ali Ta\"iga, James Assiene, Daniele Calandriello, Rahma Chaabouni, Jo\~ao Gante, Tamara von Glehn, Nate Keating, Chris Knutsen, Martin Kukla, Tianlin Liu, Ivan Lobov, Ofir Nabati, Jo\~ao Gabriel Oliveira, Nicolas Perez-Nieves, Nastasia Prutianova, Bobak Shahriari, Jean Tarbouriech, Pavel Tyletski, \c{C}a\u{g}lar \"Unl\"u, Cindy Wu, Glenn Cameron, Jerome Connor, Sertan Girgin, Maarten Grootendorst, Alon Levkovitch, Eliya Nachmani, Omar Sanseviero, Piotr Stanczyk, Quentin Berthet, Andrew Campbell, Cl\'ement Crepy, Valentin De Bortoli, Arnaud Doucet, Romuald Elie, Alexandre Galashov, Klaus Greff, Alexis Jacq, David Ruhe, Yu-Han Wu, Sebastian Flennerhag, Brendan O'Donoghue, George Scrivener, Shantanu Thakoor · 4 de agosto de 2026

  We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the sequential decoding bottlenec…

• DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language Models

  Yongkang Zhou, Xiang Xia, Cheng Yan, Fan Xu, Wuyang Zhang · 4 de agosto de 2026

  Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual conditioning a substantial recurring inference cost. Unlike autoregressive decoding, diffusion generation repeatedly revisits the entire response as …

• Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance

  Jingwei Zhang, Haoyu Lei, Zijin Feng, Jiacheng Sun, Farzan Farnia · 4 de agosto de 2026

  Although diffusion models have revolutionized continuous domains like image synthesis through high quality generations and controllable guidance mechanisms, bringing this controllability to the discrete, sequential nature of text remains an open challenge. Meanwhile, current sampling strategies and …

• Disagree to Accelerate: Closing the Loop on Diffusion Feature Forecasts

  Yanchao Li, Jiaqing Xie, Ben Gao, Wanhao Liu, Yanbo Wang, T. Y. Tsui, Jinfei Liu, Yuqiang Li, Tianfan Fu · 4 de agosto de 2026

  Training-free feature forecasting accelerates diffusion sampling by predicting features at skipped denoising steps. Recent work has mainly focused on designing stronger forecasters. Yet forecast error varies sharply across steps, and open-loop caches trust the forecast in full at every skipped step.…

• xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding

  Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim, Mudhakar Srivatsa, Raghu K. Ganti, Minjia Zhang, Naigang Wang · 4 de agosto de 2026

  Block-diffusion drafters like dFlash generate an entire block of draft tokens in a single forward pass, drastically reducing the overhead of multiple-token drafting in speculative decoding. The crucial final step of the single-pass discrete denoising process involves using the logit distribution at …

• Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors

  Alexander Scheinker · 4 de agosto de 2026

  Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against. We train a single conditional latent diffusion model that steps a dynamical system forward or backward in time via a direction flag, and show that this bidirectionality suppli…