Cross-attention control in text-conditioned models enables localized and global image edits by editing only the input text prompt.
hub Mixed citations
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Mixed citation behavior. Most common role is background (64%).
61
Pith papers citing it
2,430
external citations · Pith
Background
64% of classified citations
abstract
Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128x128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.5 and Frechet Inception Distance (FID) of 7.4, improving over the previous best IS of 52.52 and FID of 18.6.
hub tools
citation-role summary
background 7
baseline 3
method 1
citation-polarity summary
representative citing papers
DDIMs construct non-Markovian diffusion processes that share DDPM training objectives but allow much faster reverse sampling, demonstrated empirically at 10-50x wall-clock speedup.
DiffWave is a non-autoregressive diffusion model that generates high-fidelity audio waveforms from noise in constant steps, matching WaveNet vocoder quality while being orders of magnitude faster and outperforming prior models in unconditional generation.
AGAN is the first neural architecture search method for GANs that discovers architectures outperforming state-of-the-art on CIFAR-10 unsupervised image generation and competitive on supervised tasks.
DRIFT learns a structured invariance manifold from real images via one-class supervision on decomposed robust and fragile subspaces of a frozen VFM to detect AI-generated images through margin violations.
ShadeBench is a multimodal benchmark dataset for urban shade understanding that includes temporally varying shade maps, satellite imagery, building representations, and text to support shade generation, segmentation, and 3D reconstruction tasks.
SurFITR is a new collection of 137k+ surveillance-style forged images that causes existing detectors to degrade while enabling substantial gains when used for training in both in-domain and cross-domain settings.
TRM with 7M parameters achieves 45% accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, surpassing most LLMs with under 0.01% of their parameters.
Shortcut models enable high-quality single or few-step sampling in diffusion models with one network and training phase by conditioning on desired step size.
Scaled vanilla autoregressive models based on Llama achieve 2.18 FID on ImageNet 256x256 image generation, beating popular diffusion models without visual inductive biases.
Imagen achieves state-of-the-art photorealistic text-to-image generation by scaling a text-only pretrained T5 language model within a diffusion framework, reaching FID 7.27 on COCO without training on it.
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.
Modeling the differential response of real versus AI-generated images under secondary generative transformations yields state-of-the-art cross-generator detection on 19 unseen models.
Modular Diffusion Models decompose diffusion into task-specific modules to model distributions over structured visual outputs for detection, segmentation, and scene graph generation.
C-GSPN scales 2D spatial propagation to foundation vision encoders via a fast CUDA kernel, compressed blocks, and two-stage distillation, matching ViT performance with 15% fewer parameters and 4x block speedup at 2K resolution.
GPIC is a new 28-trillion-pixel permissively licensed image corpus with 100M training examples for visual generative modeling.
HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.
Fashion130K dataset and UMC framework align text and visual prompts to generate more consistent fashion outfits than prior state-of-the-art methods.
RefCD enables unsupervised category-aware object detection by using feature similarity between predicted objects and unlabeled reference images to guide category learning.
citing papers explorer
-
Prompt-to-Prompt Image Editing with Cross Attention Control
Cross-attention control in text-conditioned models enables localized and global image edits by editing only the input text prompt.
-
Denoising Diffusion Implicit Models
DDIMs construct non-Markovian diffusion processes that share DDPM training objectives but allow much faster reverse sampling, demonstrated empirically at 10-50x wall-clock speedup.
-
DiffWave: A Versatile Diffusion Model for Audio Synthesis
DiffWave is a non-autoregressive diffusion model that generates high-fidelity audio waveforms from noise in constant steps, matching WaveNet vocoder quality while being orders of magnitude faster and outperforming prior models in unconditional generation.
-
AGAN: Towards Automated Design of Generative Adversarial Networks
AGAN is the first neural architecture search method for GANs that discovers architectures outperforming state-of-the-art on CIFAR-10 unsupervised image generation and competitive on supervised tasks.
-
DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detection
DRIFT learns a structured invariance manifold from real images via one-class supervision on decomposed robust and fragile subspaces of a frozen VFM to detect AI-generated images through margin violations.
-
ShadeBench: A Benchmark Dataset for Building Shade Simulation in Sustainable Society
ShadeBench is a multimodal benchmark dataset for urban shade understanding that includes temporally varying shade maps, satellite imagery, building representations, and text to support shade generation, segmentation, and 3D reconstruction tasks.
-
SurFITR: A Dataset for Surveillance Image Forgery Detection and Localisation
SurFITR is a new collection of 137k+ surveillance-style forged images that causes existing detectors to degrade while enabling substantial gains when used for training in both in-domain and cross-domain settings.
-
Less is More: Recursive Reasoning with Tiny Networks
TRM with 7M parameters achieves 45% accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, surpassing most LLMs with under 0.01% of their parameters.
-
One Step Diffusion via Shortcut Models
Shortcut models enable high-quality single or few-step sampling in diffusion models with one network and training phase by conditioning on desired step size.
-
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Scaled vanilla autoregressive models based on Llama achieve 2.18 FID on ImageNet 256x256 image generation, beating popular diffusion models without visual inductive biases.
-
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Imagen achieves state-of-the-art photorealistic text-to-image generation by scaling a text-only pretrained T5 language model within a diffusion framework, reaching FID 7.27 on COCO without training on it.
-
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
-
Improved Denoising Diffusion Probabilistic Models
Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.
-
Do Transformations Reveal the Truth? Generative Residual Learning for Generalized AI-Generated Image Detection
Modeling the differential response of real versus AI-generated images under secondary generative transformations yields state-of-the-art cross-generator detection on 19 unseen models.
-
Modular Diffusion Models for Structured Visual Recognition
Modular Diffusion Models decompose diffusion into task-specific modules to model distributions over structured visual outputs for detection, segmentation, and scene graph generation.
-
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
C-GSPN scales 2D spatial propagation to foundation vision encoders via a fast CUDA kernel, compressed blocks, and two-stage distillation, matching ViT performance with 15% fewer parameters and 4x block speedup at 2K resolution.
-
GPIC: A Giant Permissive Image Corpus for Visual Generation
GPIC is a new 28-trillion-pixel permissively licensed image corpus with 100M training examples for visual generative modeling.
-
HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection
HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
-
Generative Recursive Reasoning
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
-
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
-
One-Step Generative Modeling via Wasserstein Gradient Flows
W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.
-
Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition
Fashion130K dataset and UMC framework align text and visual prompts to generate more consistent fashion outfits than prior state-of-the-art methods.
-
Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness
RefCD enables unsupervised category-aware object detection by using feature similarity between predicted objects and unlabeled reference images to guide category learning.
-
Intermediate Representations are Strong AI-Generated Image Detectors
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
-
Efficient Diffusion Distillation via Embedding Loss
Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.
-
Pairing Regularization for Mitigating Many-to-One Collapse in GANs
Pairing regularization mitigates intra-mode collapse in GANs by penalizing redundant latent-to-sample mappings, improving recall under collapse-prone conditions or precision under stabilized training.
-
Frequency-Aware Flow Matching for High-Quality Image Generation
FreqFlow introduces frequency-aware conditioning and a two-branch architecture to flow matching, reaching FID 1.38 on ImageNet-256 and outperforming DiT and SiT.
-
ELT: Elastic Looped Transformers for Visual Generation
Weight-shared looped transformers trained with intra-loop self-distillation match MaskGIT-class FID/FVD at roughly 4x fewer parameters and support any-time inference across loop counts.
-
Multimodal Large Language Models for Multi-Subject In-Context Image Generation
MUSIC is the first MLLM for multi-subject in-context image generation that uses an automatic data pipeline, vision chain-of-thought reasoning, and semantics-driven spatial layout planning to outperform prior methods on a new MSIC benchmark.
-
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.
-
Mirai: Autoregressive Visual Generation Needs Foresight
Mirai injects future-token foresight into autoregressive visual generators, accelerating convergence up to 10x and cutting ImageNet FID from 5.34 to 4.34.
-
How Noise Benefits AI-generated Image Detection
PiN-CLIP jointly trains a noise generator and detector under a variational positive-incentive principle to inject feature-space noise that suppresses shortcut directions and improves out-of-distribution accuracy by 5.4 points on images from 42 generative models.
-
HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
HFI detects LDM-generated images without training data by quantifying aliasing in autoencoder outputs and supports model-specific implicit watermarking.
-
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
Orthogonal subspace decomposition via SVD on vision foundation model features preserves high-rank pre-trained knowledge by freezing principal components and adapting residuals, reducing overfitting for better generalization in AI-generated image detection.
-
Gravitational-Wave Parameter Estimation in non-Gaussian noise using Score-Based Likelihood Characterization
Score-based diffusion models learn the empirical distribution of real LIGO noise to enable unbiased gravitational-wave parameter estimation under only an additivity assumption.
-
DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
DragNUWA integrates text, image, and trajectory controls into a diffusion video model using a Trajectory Sampler, Multiscale Fusion, and Adaptive Training to enable fine-grained open-domain video generation.
-
Rectified Flow: A Marginal Preserving Approach to Optimal Transport
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
A General Language Assistant as a Laboratory for Alignment
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
-
VideoGPT: Video Generation using VQ-VAE and Transformers
VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.
-
Scaling Laws for Transfer
Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.
-
Copula & Marginal Flows: Disentangling the Marginal from its Joint
CM flows disentangle marginals from joints in normalizing flows to enable exact tail asymptotics and prior CDF assumptions via copula separation.
-
MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts
MEPA adds token-routed MoE and residual self-supervised feature alignment to VAR models, reporting better FID on ImageNet 256x256 with half the training epochs and fewer parameters than dense baselines.
-
SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders
Frozen multimodal encoders enable robust AI-generated image detection via linear classification on a 10K-image curated training set that improves generalization over larger datasets.
-
Adversarial Error Correction for Visual Autoregressive Generation
AID-VAR attaches an adversarial discriminator and lightweight guidance injector to frozen VAR backbones to diagnose and correct fidelity gaps across scales, reporting 16% FID gains with 3% added parameters.
-
Dynamics of collective creativity in AI art competitions
Large-scale analysis of Artbreeder remix parties finds images simplify and converge on thematic attractors, with trade-offs between novelty, complexity, and party size in human-AI creative lineages.
-
Information theoretic underpinning of self-supervised learning by clustering
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
-
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
-
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.