Diffusion Models

Towards Provably Secure and Highly Robust Generative Image Steganography Leveraging Latent Diffusion Model AAAI 2026 Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors CVPR 2026 Towards Robust Sequential Decomposition for Complex Image Editing CVPR 2026 Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion Models AAAI 2026 Towards Storytelling Animations: Joint Synthesis of Human and Camera Motions CVPR 2026 Towards Synthesizing High-Dimensional Tabular Data with Limited Samples AAAI 2026 Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance AAAI 2026 T⋆: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning ACL 2026 Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation CVPR 2026 Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers CVPR 2026 Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers CVPR 2026 Training-free Motion Factorization for Compositional Video Generation CVPR 2026 Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback AAAI 2026 Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models CVPR 2026 Transferring Causal Driving Patterns for Generalizable Traffic Simulation with Diffusion-Based Distillation AAAI 2026 Transition Matching Distillation for Fast Video Generation CVPR 2026 Transition Models: Rethinking the Generative Learning Objective CVPR 2026 TR-DQ: Time-Rotation Diffusion Quantization AAAI 2026 TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective AAAI 2026 TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution CVPR 2026 Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models AAAI 2026 TweezeEdit: Consistent and Efficient Image Editing with Path Regularization AAAI 2026 U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences CVPR 2026 Ultra Diffusion Poser: Diffusion-Based Human Motion Tracking from Sparse Inertial Sensors and Ranging-based Between-sensor Distances CVPR 2026 UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios CVPR 2026