Diffusion Models papers, 2023–2026

Key findings

• Diffusion Models went from 660 papers in 2023 to 2,691 in 2026, roughly 4.1x in three years.
• NeurIPS publishes the most Diffusion Models work: 2,202 papers from 2023 to 2026, 32% of the four-venue total.
• The fastest-growing overlap is with Applications · chemistry physics and earth sciences: papers tagged with both rose from 14 in 2023 to 163 in 2026.
• Among the 11 topics under Deep Learning, it ranks #1 by 2026 paper count; the fastest grower in the group, Deep learning · foundation models, is up 2.5x versus 4.1x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
• ICML 2026“Do Diffusion Models Dream of Electric Planes?” Discrete and Continuous Simulation-Based Inference for Aircraft Design
• ICLR 2026$\alpha$-DPO: Robust Preference Alignment for Diffusion Models via $\alpha$ Divergence
• CVPR 20262ndMatch Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
• NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
• ICML 2025A First-order Generative Bilevel Optimization Framework for Diffusion Models
• ICLR 2025$\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps
• CVPR 20253DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
• NeurIPS 2024$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
• ICML 2024A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
• ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
• CVPR 2024D^4: Dataset Distillation via Disentangled Diffusion Model
• NeurIPS 20233D molecule generation by denoising voxel grids
• ICML 2023A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification
• ICLR 2023(Certified!!) Adversarial Robustness for Free!
• CVPR 20233D Neural Field Generation Using Triplane Diffusion
• NeurIPS 2026$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
• ICML 2026$\sigma$: Sigmoid Modulation for Ultra High Resolution Diffusion
• ICLR 2026$\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
• CVPR 20263D-LATTE Latent Space 3D Editing from Textual Instructions

All Diffusion Models papers

661 papers, page 4 of 14

151. NeurIPS 2026Directional Noise Conditioning for Diffusion Models
152. NeurIPS 2026DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
153. NeurIPS 2026Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
154. NeurIPS 2026Discrete Diffusion Playground: A 2D Benchmark for Discrete Generative Models
155. NeurIPS 2026Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
156. NeurIPS 2026Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
157. NeurIPS 2026Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
158. NeurIPS 2026Disentangled Representation Learning via Flow Matching
159. NeurIPS 2026Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
160. NeurIPS 2026Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
161. NeurIPS 2026DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation
162. NeurIPS 2026Do Diffusion Models Learn to Generalize Basic Visual Skills?
163. NeurIPS 2026Don't Match the Noise: Distribution Matching under Unknown Measurement Error with an Audit Sample
164. NeurIPS 2026Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
165. NeurIPS 2026Drifting Field Policy: Wasserstein Gradient Flow on Policy Space for Offline-to-Online RL
166. NeurIPS 2026Drifting Fields are not Conservative
167. NeurIPS 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
168. NeurIPS 2026DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
169. NeurIPS 2026DSSA: Dynamic Sparse Semantic Anchoring for Purifying Protective Perturbations against Diffusion Models
170. NeurIPS 2026Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
171. NeurIPS 2026DualDrift: Combining Forward and Reverse Drifts for One-Step Generative Modeling
172. NeurIPS 2026DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
173. NeurIPS 2026Dynamic Representation Modeling for Federated Medical Image Domain Generalization
174. NeurIPS 2026Dynamic Video Generation: Shaping Video Generation Across Time and Space
175. NeurIPS 2026Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
176. NeurIPS 2026EDISCO: Equivariant Discrete Diffusion for Euclidean Combinatorial Optimization
177. NeurIPS 2026Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
178. NeurIPS 2026Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization
179. NeurIPS 2026Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
180. NeurIPS 2026Efficient One-to-many Domain Translation via Diffusive Entropic Optimal Transport
181. NeurIPS 2026Efficient Retrosynthesis Prediction with Integral Flow Matching and Latent Inversion
182. NeurIPS 2026EGCA: A Spectral Perspective on Forward Process Design in Diffusion Models
183. NeurIPS 2026EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues
184. NeurIPS 2026Emergence of Distortions in High-Dimensional Guided Diffusion Models
185. NeurIPS 2026Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers
186. NeurIPS 2026Enabling Denoising Score Matching Type Training for Manifold Diffusion Model via Momentum and Splitting
187. NeurIPS 2026Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
188. NeurIPS 2026Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
189. NeurIPS 2026End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization
190. NeurIPS 2026Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
191. NeurIPS 2026Energy-Tweedie: Score meets Score, Energy meets Energy
192. NeurIPS 2026Enhanced convergence guarantees of score-based generative models in $\mathcal{W}_2$-distance beyond log-concavity
193. NeurIPS 2026Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion
194. NeurIPS 2026Entangled Schrödinger Bridge Matching
195. NeurIPS 2026EP-Flow: Disordered Crystal Structure Prediction without Site-level Annotation
196. NeurIPS 2026EpicWorldModel: Exploration-driven Planning with Latent World Models
197. NeurIPS 2026Epigenomics-Guided Flow Matching for 3D Genome Super-Resolution
198. NeurIPS 2026Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
199. NeurIPS 2026Escaping the Curse of Dimensionality in One‑Step Flow-Based Generative Models
200. NeurIPS 2026ESS-Flow: training-free guidance as Bayesian inference in source space

FAQ

How many Diffusion Models papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

6,900 in total: 660 in 2023, 1,471 in 2024, 2,078 in 2025, 2,691 in 2026.

How many Diffusion Models papers are at NeurIPS 2026?

NeurIPS 2026 has 661 Diffusion Models papers, versus 694 the year before.

How many Diffusion Models papers are at ICLR 2026?

ICLR 2026 has 694 Diffusion Models papers, versus 487 the year before.

How many Diffusion Models papers are at ICML 2026?

ICML 2026 has 728 Diffusion Models papers, versus 346 the year before.

How many Diffusion Models papers are at CVPR 2026?

CVPR 2026 has 608 Diffusion Models papers, versus 551 the year before.

Which conference publishes the most Diffusion Models papers?

NeurIPS, with 2,202 papers from 2023 to 2026.