Generative Adversarial Networks and Image Synthesis

Derniers papiers

• 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 juillet 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…

• TILDE: TILt-based Distributional Erasure for Concept Unlearning

  Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji · 8 juillet 2026

  Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remo…

• 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 juillet 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…

• FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models

  Bowen Xue, Zihan Min, Xingyang Li, Zhekai Zhang, Haocheng Xi, Lvmin Zhang, Maneesh Agrawala, Jun-Yan Zhu, Song Han, Yujun Lin, Muyang Li · 8 juillet 2026

  Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footprints and slow traini…

• Replication in Visual Diffusion Models: A Survey and Outlook

  Wenhao Wang, Yifan Sun, Zongxin Yang, Zhengdong Hu, Zhentao Tan, Yi Yang · 8 juillet 2026

  Visual diffusion models have revolutionized the field of creative AI, producing high-quality and diverse content. However, they inevitably memorize training images or videos, subsequently replicating their concepts, content, or styles during inference. This phenomenon raises significant concerns abo…

• x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability

  Xin Peng, Ang Gao · 8 juillet 2026

  Diffusion and flow matching models generate high-quality samples, but their ODE samplers often need tens to hundreds of neural function evaluations (NFEs). This remains a practical challenge for released checkpoints, since many accelerators require additional design choices and training cost through…

• Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders

  Yoav Baron, Sara Dorfman, Roni Paiss, Daniel Cohen-Or, Or Patashnik · 8 juillet 2026

  Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities. While standalone VLMs demonstrate strong localization capabilities, editing pipelines frequently struggle to maintain this…

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

  Evelyn Turri, Davide Bucciarelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia · 8 juillet 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…

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

  Jeanie Schreiber, Tyrus Berry, Zeeshan Ahmed · 8 juillet 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…

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

  Girum Demisse · 8 juillet 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…

• A Constrained Optimization Perspective of Unrolled Transformers

  Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro · 8 juillet 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…

• Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation

  Anna C\'ordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jes\'us Olivera · 8 juillet 2026

  We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning. PACR-Video keeps a text-to-video diffusion transformer frozen and augments it wi…

• Inclusive KL Gradient Flows: Otto-Wasserstein, Fisher-Rao-Gaussian, and Local-Estimator Dynamics

  Jia-Jie Zhu · 7 juillet 2026

  Otto's Wasserstein gradient flow of the inclusive (forward) Kullback--Leibler (KL) divergence offers a principled framework for analyzing statistical inference algorithms, yet algorithms targeting the exclusive (reverse) KL divergence are rarely studied with such tools. We establish a unified gradie…

• Reflected Schr\"odinger Bridge Matching

  Marcus H\"aggbom, Viktor Nilsson, Pierre Nyquist, Joakim and\'en · 7 juillet 2026

  Recent advances in generative modeling have enabled the efficient computation of Schr\"odinger bridges (SB) in high-dimensional settings by leveraging partially simulation-free training methods inspired by flow matching. However, these have not covered SBs with reflecting dynamics, a useful model ch…

• Is Generation Required for Data-Efficient Perception?

  Jack Brady, Bernhard Sch\"olkopf, Thomas Kipf, Simon Buchholz, Wieland Brendel · 7 juillet 2026

  It has been hypothesized that achieving the data efficiency of human 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 representat…

• CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation

  Xuyao Huang, Zelai Deng, Xu Wang, Xizhong Xiao, Zhijie Deng · 7 juillet 2026

  The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, slow motion, etc. While Diffusion Transformers (DiTs) exhibit strong performance in video generation, their large parameter sizes and multi-step iterati…

• Towards Diverse and Comprehensive Benchmarks for Mutual Information Estimation

  Alberto Foresti, Ivan Butakov, Alexander Tolmachev, Giulio Franzese, Alexey Frolov, Pietro Michiardi · 7 juillet 2026

  Mutual information (MI) estimation is a central problem in machine learning and statistics; however, existing benchmarks typically evaluate estimators on simplified, low-dimensional distributions, leaving their performance on complex, realistic data largely unexplored. We address this gap with a com…

• Separating Representation from Reconstruction Enables Scalable Text Encoders

  Megi Dervishi, Mathurin Videau, Yann LeCun · 7 juillet 2026

  While decoders have rapidly scaled, encoders have remained largely unchanged since BERT. We revisit this disparity by frozen backbone evaluation via probing. Under this lens, the representations of BERT encoders become increasingly $\textit{unexploitable}$ by frozen probes, despite improved perplexi…

• LGQ: Learnable Geometric Quantization for Image Tokenization

  Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic, Hasan Kurban · 7 juillet 2026

  Recent collapse-free quantizers such as FSQ achieve stable training by replacing the learnable codebook with an engineered geometry: a fixed scalar grid whose structure is dictated by the codebook size K. We show this trade-off is unnecessary. We introduce Learnable Geometric Quantization (LGQ), whi…

• Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models

  Shijin Gong, Baihua He, Xinyu Zhang · 7 juillet 2026

  Conditional generative models have emerged as powerful tools for sampling from target conditional distributions, driving substantial advances across a wide range of scientific and applied domains. As these models proliferate, practitioners often face multiple plausible generators whose performance c…

• Tightening the Score Matching Gap for Diffusion Models

  Benjamin Dupuis, Tyler Farghly, Maxime Haddouche, Alain Durmus, Umut Simsekli · 7 juillet 2026

  Diffusion models (DMs) are a state-of-the-art generative method to approximately sample from an unknown distribution. Their training and evaluation primarily rely on an Evidence Lower Bound (ELBO), which relates the Kullback-Leibler (KL) divergence of model samples to the score matching loss along t…

• SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness

  Jongyeop Hyun, Hyounghun Kim · 7 juillet 2026

  Deploying AI-generated video detectors in real-world services demands an ultra-low false positive rate (FPR) on real videos to avoid falsely rejecting authentic content, a regime where standard metrics such as AUROC fail to reflect actual operating behavior. We introduce Spatial Patch-Level Incohere…

• Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

  Disheng Liu, Tuo Liang, Chaoda Song, Yu Yin · 7 juillet 2026

  Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models. Existing approaches to exploiting this potential typically involve 1) training or fine-tuning generators, or 2) using lightweight post-hoc adaptation like prompt engin…

• Vidu S1: A Real-Time Interactive Video Generation Model

  Jintao Zhang, Kai Jiang, Jintao Chen, Xu Wang, Yang Luo, Yuji Wang, Dechuang Chen, Jungang Li, Chengyang Ye, Marco Chen, Hongzhou Zhu, Min Zhao, Yuxuan Jiang, Zhengkun Huang, Chendong Xiang, Kaiwen Zheng, Haoxu Wang, Xiaohang Wang, Qi Jia, Xin Chen, Yimin Chen, Youhe Jiang, Fangcheng Fu, Zhijie Deng, Fan Bao, Jianfei Chen, Jun Zhu · 7 juillet 2026

  We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual dis…

• Constrained Flow Matching via Lagrangian Dual Flows

  Vince Kurtz, Alexander Davydov · 7 juillet 2026

  Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, planning, and physics require inference-time constraints on generated outputs. Such constraints are often complex and highly nonlinear. As a result, methods designed for linear constraints like image inp…