Deep learning · generative models and autoencoders papers, 2023–2026

Key findings

• Deep learning · generative models and autoencoders went from 1,216 papers in 2023 to 1,430 in 2026, roughly 1.2x in three years.
• NeurIPS publishes the most Deep learning · generative models and autoencoders work: 1,714 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with Image Generation: papers tagged with both rose from 35 in 2023 to 150 in 2026.
• Among the 11 topics under Deep Learning, it ranks #2 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 1.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Critical $\beta$-Scale for Posterior Collapse in Dirichlet $\beta$-VAEs
• ICML 2026(1D) Ordered Tokens Enable Efficient Test-Time Search
• ICLR 2026``Noisier'’ Noise Contrastive Estimation is (Almost) Maximum Likelihood
• CVPR 2026Anchoring and Rescaling Attention for Semantically Coherent Inbetweening
• NeurIPS 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
• ICML 2025A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
• ICLR 2025A Watermark for Order-Agnostic Language Models
• CVPR 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
• NeurIPS 2024[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
• ICML 2024A Fixed-Point Approach for Causal Generative Modeling
• ICLR 2024$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
• CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
• NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
• ICML 2023A Kernelized Stein Discrepancy for Biological Sequences
• ICLR 2023Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing
• CVPR 20233D GAN Inversion With Facial Symmetry Prior
• NeurIPS 2026Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
• ICML 2026$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
• ICLR 2026Analyzing and Evaluating Unbiased Language Model Watermark
• CVPR 2026Bidirectional Normalizing Flow From Data to Noise and Back

All Deep learning · generative models and autoencoders papers

240 papers, page 3 of 5

101. NeurIPS 2025HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
102. NeurIPS 2025How many measurements are enough? Bayesian recovery in inverse problems with general distributions
103. NeurIPS 2025Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings
104. NeurIPS 2025Image Super-Resolution with Guarantees via Conformalized Generative Models
105. NeurIPS 2025Implicit Generative Property Enhancer
106. NeurIPS 2025Improved Training Technique for Shortcut Models
107. NeurIPS 2025Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
108. NeurIPS 2025Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
109. NeurIPS 2025In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain
110. NeurIPS 2025Inference with correlated priors using sisters cells
111. NeurIPS 2025Information Theoretic Learning for Diffusion Models with Warm Start
112. NeurIPS 2025Informed Correctors for Discrete Diffusion Models
113. NeurIPS 2025Is Your Diffusion Model Actually Denoising?
114. NeurIPS 2025JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensemble Generation
115. NeurIPS 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
116. NeurIPS 2025KLASS: KL-Guided Fast Inference in Masked Diffusion Models
117. NeurIPS 2025Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
118. NeurIPS 2025Knowledge Starts with Practice: Knowledge-Aware Exercise Generative Recommendation with Adaptive Multi-Agent Cooperation
119. NeurIPS 2025Large Language Diffusion Models
120. NeurIPS 2025Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
121. NeurIPS 2025Learning conformational ensembles of proteins based on backbone geometry
122. NeurIPS 2025Learning Diffusion Models with Flexible Representation Guidance
123. NeurIPS 2025Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization
124. NeurIPS 2025Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
125. NeurIPS 2025Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding
126. NeurIPS 2025Learning to Integrate Diffusion ODEs by Averaging the Derivatives
127. NeurIPS 2025Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
128. NeurIPS 2025LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
129. NeurIPS 2025Locality in Image Diffusion Models Emerges from Data Statistics
130. NeurIPS 2025Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation
131. NeurIPS 2025Low Rank Gradients and Where to Find Them
132. NeurIPS 2025Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
133. NeurIPS 2025Mean Flows for One-step Generative Modeling
134. NeurIPS 2025Measuring and Guiding Monosemanticity
135. NeurIPS 2025Missing Data Imputation by Reducing Mutual Information with Rectified Flows
136. NeurIPS 2025MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
137. NeurIPS 2025Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data
138. NeurIPS 2025Multivariate Time Series Anomaly Detection with Idempotent Reconstruction
139. NeurIPS 2025Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
140. NeurIPS 2025Neural Correlates of Serial Dependence: Synaptic Short-term Plasticity Orchestrates Repulsion and Attraction
141. NeurIPS 2025Non-Markovian Discrete Diffusion with Causal Language Models
142. NeurIPS 2025On scalable and efficient training of diffusion samplers
143. NeurIPS 2025On the Relation between Rectified Flows and Optimal Transport
144. NeurIPS 2025One-Step Diffusion-Based Image Compression with Semantic Distillation
145. NeurIPS 2025Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization
146. NeurIPS 2025Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
147. NeurIPS 2025Orientation Matters: Making 3D Generative Models Orientation-Aligned
148. NeurIPS 2025PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
149. NeurIPS 2025PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling
150. NeurIPS 2025PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis

FAQ

How many Deep learning · generative models and autoencoders papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

4,314 in total: 1,216 in 2023, 768 in 2024, 900 in 2025, 1,430 in 2026.

How many Deep learning · generative models and autoencoders papers are at NeurIPS 2026?

NeurIPS 2026 has 349 Deep learning · generative models and autoencoders papers, versus 240 the year before.

How many Deep learning · generative models and autoencoders papers are at ICLR 2026?

ICLR 2026 has 303 Deep learning · generative models and autoencoders papers, versus 275 the year before.

How many Deep learning · generative models and autoencoders papers are at ICML 2026?

ICML 2026 has 604 Deep learning · generative models and autoencoders papers, versus 275 the year before.

How many Deep learning · generative models and autoencoders papers are at CVPR 2026?

CVPR 2026 has 174 Deep learning · generative models and autoencoders papers, versus 110 the year before.

Which conference publishes the most Deep learning · generative models and autoencoders papers?

NeurIPS, with 1,714 papers from 2023 to 2026.