← Models

Deep Learning › Models ›

Diffusion Models

4342 directly classified papers

Papers per year

Papers

Gentle Manipulation Policy Learning via Demonstrations from VLM Planned Atomic Skills AAAI 2026

DiM-TS: Bridge the Gap Between Selective State Space Models and Time Series for Generative Modeling AAAI 2026

Modeling Item-Level Dynamic Variability with Residual Diffusion for Bundle Recommendation AAAI 2026

Gracefully Air-Written: Enhancing the Legibility and Style Consistency of In-Air Handwriting AAAI 2026

Emotion-Conditioned Motion Sub-spaces with Flow Matching for Real-Time Audio-Driven Talking Heads AAAI 2026

Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection AAAI 2026

ARDiff: Anisotropic Residual Diffusion for Heterogeneous Graph Learning AAAI 2026

Inference-time Scaling for Diffusion-based Audio Super-resolution AAAI 2026

Towards Synthesizing High-Dimensional Tabular Data with Limited Samples AAAI 2026

MIGDiff: Multi-attributes Imputations for Attribute-missing Graphs via Graph Denoising Diffusion Model AAAI 2026

Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection AAAI 2026

WaveDiST: A Wavelet Diffusion Transformer for Spatio-Temporal Estimation on Unobserved Locations AAAI 2026

Knowledge Graph Guided Heterogeneity-Informed Diffusion Model for Spatio-Temporal Generation AAAI 2026

Diffusion Distillation with Direct Preference Optimization for Efficient 3D LiDAR Scene Completion AAAI 2026

CondDiff-AMO: Integrating Conditional Diffusion Mechanism for Unified Amodal Mask Generation AAAI 2026

MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss AAAI 2026

ObjectAdv: Object-Level Unrestricted Adversarial Attacks via Diffusion Models AAAI 2026

DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model AAAI 2026

Studying Classifier(-Free) Guidance from a Classifier-Centric Perspective AAAI 2026

Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion AAAI 2026

Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers AAAI 2026

Oscillation Inversion: Training-Free Image and Video Enhancement Through Oscillated Latents in Large Flow Models AAAI 2026

M3ashy: Multi-Modal Material Synthesis via Hyperdiffusion AAAI 2026

IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation AAAI 2026

Exploring Position Encoding Mechanism in Diffusion U-Net for Training-free High-resolution Image Generation AAAI 2026