Description
Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound (https://arxiv.org/abs/2006.11239).
Papers Using This Method
Similarity-Guided Diffusion for Contrastive Sequential Recommendation2025-07-16CATVis: Context-Aware Thought Visualization2025-07-15Exploring the robustness of TractOracle methods in RL-based tractography2025-07-15HUG-VAS: A Hierarchical NURBS-Based Generative Model for Aortic Geometry Synthesis and Controllable Editing2025-07-15Implementing Adaptations for Vision AutoRegressive Model2025-07-15Diffusion Decoding for Peptide De Novo Sequencing2025-07-15AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air2025-07-15Latent Space Consistency for Sparse-View CT Reconstruction2025-07-15When and Where do Data Poisons Attack Textual Inversion?2025-07-11Omni-Video: Democratizing Unified Video Understanding and Generation2025-07-08Modern Methods in Associative Memory2025-07-08CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions2025-07-08Normalizing Diffusion Kernels with Optimal Transport2025-07-08Unconditional Diffusion for Generative Sequential Recommendation2025-07-08T-LoRA: Single Image Diffusion Model Customization Without Overfitting2025-07-08Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation2025-07-08SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning2025-07-08DreamArt: Generating Interactable Articulated Objects from a Single Image2025-07-08Prompt-Free Conditional Diffusion for Multi-object Image Augmentation2025-07-08ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models2025-07-08