Generative Models

Time Series Forecasting via Direct Per-Step Probability Distribution Modeling AAAI 2026 Towards Illumination-Aware Restoration of Metalens-Captured Images: A New Dataset and a Strong Baseline AAAI 2026 Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency Differencing AAAI 2026 Towards Provably Secure and Highly Robust Generative Image Steganography Leveraging Latent Diffusion Model AAAI 2026 Tractable Sharpness-Aware Learning of Probabilistic Circuits AAAI 2026 TTVAE: Transformer-Based Generative Modeling for Tabular Data Generation (Abstract Reprint) AAAI 2026 Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics AAAI 2026 Understanding, Accelerating, and Improving MeanFlow Training CVPR 2026 Understanding Generative AI Capabilities in Everyday Image Editing Tasks WACV 2026 Unified Number-Free Text-to-Motion Generation Via Flow Matching CVPR 2026 Unified Thinker: A General Reasoning Core for Image Generation ACL 2026 UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts ACL 2026 UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matching CVPR 2026 Universal Learning of Stochastic Dynamics for Exact Belief Propagation Using Bernstein Normalizing Flows AAAI 2026 UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders CVPR 2026 VeriFlow: Modeling Distributions for Neural Network Verification AAAI 2026 VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations CVPR 2026 VisiLock: Authorizing Instruction-based Image editing with Dual Score Distillation CVPR 2026 VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation AAAI 2026 Walk Before You Dance: High-fidelity and Editable Dance Synthesis via Generative Masked Motion Prior AAAI 2026 When Anonymity Breaks: Identifying Models Behind Text-to-Image Leaderboards CVPR 2026 WonderZoom: Multi-Scale 3D World Generation CVPR 2026 WorldGrow: Generating Infinite 3D World AAAI 2026 Your Classifier Can Do More: Towards Balancing the Gaps in Classification, Robustness, and Generation CVPR 2026 Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation AAAI 2026