Diffusion Models

SADA: Stability-guided Adaptive Diffusion Acceleration ICML 2025 SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders ICML 2025 SafeBimanual: Diffusion-based trajectory optimization for safe bimanual manipulation CoRL 2025 SafeDiffuser: Safe Planning with Diffusion Probabilistic Models ICLR 2025 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks ICCV 2025 SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation ICLR 2025 SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing CVPR 2025 Sample-specific Noise Injection for Diffusion-based Adversarial Purification ICML 2025 Sampling Binary Data by Denoising through Score Functions ICML 2025 Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold AISTATS 2025 Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations AISTATS 2025 SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer ICML 2025 SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers ICLR 2025 SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation ICCV 2025 SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation ICLR 2025 SAS: Segment Any 3D Scene with Integrated 2D Priors ICCV 2025 Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion ICCV 2025 Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution CVPR 2025 Satellite to GroundScape - Large-scale Consistent Ground View Generation from Satellite Views CVPR 2025 SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection AAAI 2025 SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion ICML 2025 Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics ICLR 2025 Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment ICML 2025 Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling ICCV 2025 Scaling Diffusion Language Models via Adaptation from Autoregressive Models ICLR 2025