Latest Research in Generative Adversarial Networks and Image Synthesis

Top Research Topics in Generative Adversarial Networks and Image Synthesis

• Computer Vision and Pattern Recognition — 65 papers
• Machine Learning — 23 papers
• Machine Learning — 4 papers
• Generative Adversarial Networks and Image Synthesis — 3 papers
• Artificial Intelligence — 2 papers
• Domain Adaptation and Few-Shot Learning — 2 papers
• Mineral Processing and Grinding — 1 papers
• Homotopy and Cohomology in Algebraic Topology — 1 papers
• Visual perception and processing mechanisms — 1 papers
• Signal Processing — 1 papers

Highest-Cited Papers

1. Fine-tune the stable diffusion model using mindat data to generate mineral images from textual descriptions of attribute combinations
2. Null Dictionary Theory: Geometry, Groupoids, and Sparse Functorial Learning
3. Perceptual misalignment of texture representations in convolutional neural networks
4. Training Flow Matching: The Role of Weighting and Parameterization
5. Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network
6. A Smaller Transformer in Your Transformer
7. Recency Forcing: Bridging the Long-Horizon Gap in Autoregressive Video Generation
8. DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-Step Video Diffusion Models
9. SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition
10. Transformation Laws in Neural Representations: Structure, Realisability, and Construction
11. Achieving Out-of-Distribution Generalization via Conditional-Mechanism Stability (CR-ODG)
12. Achieving Out-of-Distribution Generalization via Conditional-Mechanism Stability (CR-ODG)
13. vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes
14. CineScale: Tuning-Free High-Resolution Video Generation
15. Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows
16. Efficient generative adversarial networks using linear additive-attention Transformers
17. Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision
18. Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
19. Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds
20. Product Manifold Flow Matching: Low-NFE Generative Efficiency and Domain-Dependent Finite-Step Quality Optima