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

776 papers, page 3 of 16

101. NeurIPS 2023CAT-Walk: Inductive Hypergraph Learning via Set Walks
102. NeurIPS 2023CBD: A Certified Backdoor Detector Based on Local Dominant Probability
103. NeurIPS 2023Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
104. NeurIPS 2023Certification of Distributional Individual Fairness
105. NeurIPS 2023Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
106. NeurIPS 2023Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
107. NeurIPS 2023CHAMMI: A benchmark for channel-adaptive models in microscopy imaging
108. NeurIPS 2023Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception
109. NeurIPS 2023Change point detection and inference in multivariate non-parametric models under mixing conditions
110. NeurIPS 2023Characterization and Learning of Causal Graphs with Small Conditioning Sets
111. NeurIPS 2023Characterizing Out-of-Distribution Error via Optimal Transport
112. NeurIPS 2023Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models
113. NeurIPS 2023Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark
114. NeurIPS 2023ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling
115. NeurIPS 2023ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning
116. NeurIPS 2023Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits
117. NeurIPS 2023Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
118. NeurIPS 2023Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections
119. NeurIPS 2023CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
120. NeurIPS 2023Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
121. NeurIPS 2023Collaborative Learning via Prediction Consensus
122. NeurIPS 2023Collapsed Inference for Bayesian Deep Learning
123. NeurIPS 2023CoLLAT: On Adding Fine-grained Audio Understanding to Language Models using Token-Level Locked-Language Tuning
124. NeurIPS 2023Combinatorial Group Testing with Selfish Agents
125. NeurIPS 2023Combining Behaviors with the Successor Features Keyboard
126. NeurIPS 2023Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems
127. NeurIPS 2023Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions
128. NeurIPS 2023Complexity Matters: Rethinking the Latent Space for Generative Modeling
129. NeurIPS 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
130. NeurIPS 2023Compositional Generalization from First Principles
131. NeurIPS 2023Compositional Sculpting of Iterative Generative Processes
132. NeurIPS 2023Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy
133. NeurIPS 2023Concept Algebra for (Score-Based) Text-Controlled Generative Models
134. NeurIPS 2023Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
135. NeurIPS 2023Conditional independence testing under misspecified inductive biases
136. NeurIPS 2023Conditional score-based diffusion models for Bayesian inference in infinite dimensions
137. NeurIPS 2023Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems
138. NeurIPS 2023Connecting Pre-trained Language Model and Downstream Task via Properties of Representation
139. NeurIPS 2023Conservative State Value Estimation for Offline Reinforcement Learning
140. NeurIPS 2023Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent
141. NeurIPS 2023Contextual Bandits and Imitation Learning with Preference-Based Active Queries
142. NeurIPS 2023Contextually Affinitive Neighborhood Refinery for Deep Clustering
143. NeurIPS 2023Continuous-Time Functional Diffusion Processes
144. NeurIPS 2023Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time
145. NeurIPS 2023Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
146. NeurIPS 2023Contrastive Sampling Chains in Diffusion Models
147. NeurIPS 2023Contrastive Training of Complex-Valued Autoencoders for Object Discovery
148. NeurIPS 2023Convolutional Neural Operators for robust and accurate learning of PDEs
149. NeurIPS 2023Coop: Memory is not a Commodity
150. NeurIPS 2023CORL: Research-oriented Deep Offline Reinforcement Learning Library

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.