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 10 of 87

451. ICLR 2026There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models
452. ICLR 2026Think Then Embed: Generative Context Improves Multimodal Embedding
453. ICLR 2026Time-Gated Multi-Scale Flow Matching for Time-Series Imputation
454. ICLR 2026ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
455. ICLR 2026Topological Flow Matching
456. ICLR 2026Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
457. ICLR 2026Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connections
458. ICLR 2026TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models
459. ICLR 2026Tree-sliced Sobolev IPM
460. ICLR 2026TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
461. ICLR 2026Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression
462. ICLR 2026Two-Layer Convolutional Autoencoders Trained on Normal Data Provably Detect Unseen Anomalies
463. ICLR 2026Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
464. ICLR 2026Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives
465. ICLR 2026Untraceable DeepFakes via Traceable Fingerprint Elimination
466. ICLR 2026Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
467. ICLR 2026Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
468. ICLR 2026VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers
469. ICLR 2026What Exactly Does Guidance Do in Masked Discrete Diffusion Models
470. ICLR 2026What Generative Search Engines Like and How to Optimize Web Content Cooperatively
471. ICLR 2026What happens when generative AI models train recursively on each others' outputs?
472. ICLR 2026When LLMs get significantly worse: A statistical approach to detect model degradations
473. ICLR 2026When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
474. ICLR 2026WithAnyone: Toward Controllable and ID Consistent Image Generation
475. ICLR 2026Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
476. ICLR 2026ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
477. ICLR 2026ZIP-RC: Zero-overhead Inference-time Prediction of Reward and Cost for Adaptive and Interpretable Generation
478. ICML 2026(1D) Ordered Tokens Enable Efficient Test-Time Search
479. ICML 2026$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
480. ICML 20263D MeanFlow: One-Step Point Cloud Completion and Generation via Average-Velocity Transport
481. ICML 2026A Diffusive Classification Loss for Learning Energy-based Generative Models
482. ICML 2026A Flat Vocabulary or a Rich Hierarchy? Re-introducing Intrinsic Structure Transforms the Autoregressive Image Generation
483. ICML 2026A Kinetic Energy Perspective of Flow Matching
484. ICML 2026A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
485. ICML 2026A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms
486. ICML 2026A Solvable High-Dimensional Model Where Nonlinear Autoencoders Learn Structure Invisible to PCA While Test Loss Misaligns With Generalization
487. ICML 2026A Theoretical Framework for Statistical Evaluability of Generative Models
488. ICML 2026A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching
489. ICML 2026A Unifying View of Variational Generative Wasserstein Flows
490. ICML 2026AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation
491. ICML 2026Adapting Noise to Data: Generative Flows from Learned 1D Processes
492. ICML 2026Adversarial Flow Models
493. ICML 2026Adversarial Latent Embedding Repair for LLM Continual Learning
494. ICML 2026Align Your Trajectory Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
495. ICML 2026Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
496. ICML 2026Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
497. ICML 2026Ambient Dataloops: Generative Models for Dataset Refinement
498. ICML 2026Amortized Maximum Inner Product Search with Learned Support Functions
499. ICML 2026An Interactive Paradigm for Deep Research
500. ICML 2026Analytic Bijections for Smooth and Interpretable Normalizing Flows

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.