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

4,314 papers, page 38 of 87

1851. ICML 2025Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World
1852. ICML 2025Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
1853. ICML 2025Compositional Condition Question Answering in Tabular Understanding
1854. ICML 2025Compositional Scene Understanding through Inverse Generative Modeling
1855. ICML 2025Compressed Image Generation with Denoising Diffusion Codebook Models
1856. ICML 2025Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
1857. ICML 2025Concept Reachability in Diffusion Models: Beyond Dataset Constraints
1858. ICML 2025Concept-Centric Token Interpretation for Vector-Quantized Generative Models
1859. ICML 2025ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
1860. ICML 2025Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting
1861. ICML 2025Continuous Semi-Implicit Models
1862. ICML 2025Continuous Visual Autoregressive Generation via Score Maximization
1863. ICML 2025Controlled Generation with Equivariant Variational Flow Matching
1864. ICML 2025D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
1865. ICML 2025DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
1866. ICML 2025DeFoG: Discrete Flow Matching for Graph Generation
1867. ICML 2025Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
1868. ICML 2025Density Ratio Estimation with Conditional Probability Paths
1869. ICML 2025Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models
1870. ICML 2025Differentiable Solver Search for Fast Diffusion Sampling
1871. ICML 2025Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
1872. ICML 2025Diffusion Adversarial Post-Training for One-Step Video Generation
1873. ICML 2025Diffusion Counterfactual Generation with Semantic Abduction
1874. ICML 2025Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation
1875. ICML 2025Diffusion Sampling Correction via Approximately 10 Parameters
1876. ICML 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
1877. ICML 2025Direct Motion Models for Assessing Generated Videos
1878. ICML 2025Discrete Markov Probabilistic Models: An Improved Discrete Score-Based Framework with sharp convergence bounds under minimal assumptions
1879. ICML 2025Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
1880. ICML 2025Distillation of Discrete Diffusion through Dimensional Correlations
1881. ICML 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
1882. ICML 2025Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
1883. ICML 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
1884. ICML 2025EasyInv: Toward Fast and Better DDIM Inversion
1885. ICML 2025EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
1886. ICML 2025Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
1887. ICML 2025Effective and Efficient Masked Image Generation Models
1888. ICML 2025Efficient Diffusion Models for Symmetric Manifolds
1889. ICML 2025Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
1890. ICML 2025Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
1891. ICML 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
1892. ICML 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
1893. ICML 2025Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers
1894. ICML 2025Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation
1895. ICML 2025Ensemble Distribution Distillation via Flow Matching
1896. ICML 2025Epsilon-VAE: Denoising as Visual Decoding
1897. ICML 2025EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
1898. ICML 2025Ergodic Generative Flows
1899. ICML 2025Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
1900. ICML 2025Exponential Family Variational Flow Matching for Tabular Data Generation

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.