Diffusion Models papers, 2023–2026
Diffusion, flow matching, and score-based generative modeling
Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 6,900 papers are tagged with this topic.
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.
Papers per venue
Counts by year and venue
| Year | NeurIPS | ICLR | ICML | CVPR | Total |
|---|---|---|---|---|---|
| 2023 | 327 | 86 | 109 | 138 | 660 |
| 2024 | 520 | 260 | 195 | 496 | 1,471 |
| 2025 | 694 | 487 | 346 | 551 | 2,078 |
| 2026 | 661 | 694 | 728 | 608 | 2,691 |
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
2,078 papers, page 38 of 42
- NeurIPS 2025Probing Equivariance and Symmetry Breaking in Convolutional Networks
- NeurIPS 2025Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
- NeurIPS 2025Projection-Manifold Regularized Latent Diffusion for Robust General Image Fusion
- NeurIPS 2025Promptable 3-D Object Localization with Latent Diffusion Models
- NeurIPS 2025Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
- NeurIPS 2025Quantifying Cross-Modality Memorization in Vision-Language Models
- NeurIPS 2025Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation
- NeurIPS 2025Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback
- NeurIPS 2025Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion
- NeurIPS 2025Rare Text Semantics Were Always There in Your Diffusion Transformer
- NeurIPS 2025Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape
- NeurIPS 2025Real-Time Execution of Action Chunking Flow Policies
- NeurIPS 2025ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection
- NeurIPS 2025Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
- NeurIPS 2025Rectified CFG++ for Flow Based Models
- NeurIPS 2025ReDi: Rectified Discrete Flow
- NeurIPS 2025REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion Planning
- NeurIPS 2025ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
- NeurIPS 2025Reinforced Context Order Recovery for Adaptive Reasoning and Planning
- NeurIPS 2025Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
- NeurIPS 2025Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
- NeurIPS 2025RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
- NeurIPS 2025Remasking Discrete Diffusion Models with Inference-Time Scaling
- NeurIPS 2025Removing Concepts from Text-to-Image Models with Only Negative Samples
- NeurIPS 2025REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
- NeurIPS 2025RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation
- NeurIPS 2025Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
- NeurIPS 2025Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-design
- NeurIPS 2025Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
- NeurIPS 2025RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation
- NeurIPS 2025Rethinking Losses for Diffusion Bridge Samplers
- NeurIPS 2025RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step Retrosynthesis
- NeurIPS 2025Reverse Diffusion Sequential Monte Carlo Samplers
- NeurIPS 2025Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws
- NeurIPS 2025Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
- NeurIPS 2025Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
- NeurIPS 2025RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching
- NeurIPS 2025RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching
- NeurIPS 2025Riemannian Consistency Model
- NeurIPS 2025Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry
- NeurIPS 2025RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation
- NeurIPS 2025Robustness in Both Domains: CLIP Needs a Robust Text Encoder
- NeurIPS 2025RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
- NeurIPS 2025ROGR: Relightable 3D Objects using Generative Relighting
- NeurIPS 2025Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate Decomposition
- NeurIPS 2025RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
- NeurIPS 2025ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge
- NeurIPS 2025RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
- NeurIPS 2025ROSE: Remove Objects with Side Effects in Videos
- NeurIPS 2025RrED: Black-box Unsupervised Domain Adaptation via Rectifying-reasoning Errors of Diffusion
Ask about this trend from Claude or Cursor
Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.
Copy this prompt into your assistant
Use paperlist to show how Diffusion Models papers grew at NeurIPS from 2023 to 2026, and which year jumped the most.
Tool the assistant calls: get_topic_stats {"topic": "diffusion-models"}
Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)
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.
More in Deep Learning
- Deep learning · generative models and autoencoders 4,314
- Deep learning · large language models 2,334
- Deep learning · self supervised learning 1,958
- Deep learning · graph neural networks 1,648
- Deep learning · optimization 953
- Deep learning · representation learning 802
- Deep learning · probabilistic methods 637
- Deep learning · foundation models 536
- Deep learning · causal inference 316
- Deep learning · transfer learning 197