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

349 papers, page 5 of 7

201. NeurIPS 2026Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers
202. NeurIPS 2026Normalizing Trajectory Models
203. NeurIPS 2026Not Suppressing or Purifying: Backdoor Containment via Expert Quarantine and Shutdown in LLMs
204. NeurIPS 2026Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
205. NeurIPS 2026On approximation and estimation of Schrödinger potentials without the curse of dimensionality
206. NeurIPS 2026On the Depth of Monotone ReLU Neural Networks and ICNNs
207. NeurIPS 2026On the Selectivity of Generative Models in Structure-Based Drug Design
208. NeurIPS 2026On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
209. NeurIPS 2026On the Tightness and Computational Tractability of Higher-Dimensional Confidence Sequences
210. NeurIPS 2026One-Shot Generative Flows: Existence and Obstructions
211. NeurIPS 2026OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
212. NeurIPS 2026Optimistic Dual Averaging Unifies Modern Optimizers
213. NeurIPS 2026Order-Optimal Sample Complexity for Distribution Learning via Flow Matching
214. NeurIPS 2026Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
215. NeurIPS 2026PatchBench: Measuring Collateral Damage in Activation Patching
216. NeurIPS 2026Patching Up Circuit Learning on Images
217. NeurIPS 2026Path-independent Flow Matching for Multi-parameter Generative Dynamics
218. NeurIPS 2026PEEK: One-Step Look-Ahead Exposure Bias Correction for Diffusion Sampling
219. NeurIPS 2026Permutation-Invariant Spectral Learning via Dyson Diffusion
220. NeurIPS 2026Phase Kernel Lifts Capacity of Dense Associative Memory
221. NeurIPS 2026PhaseDance: Capturing Rhythm and Expressivity in Dance Modeling
222. NeurIPS 2026PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
223. NeurIPS 2026Plan4D: Generative Plannable 4D Worlds
224. NeurIPS 2026Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser
225. NeurIPS 2026Point-to-Manifold Geometry: Flexibly Overcoming the Curse of Dimensionality in Neural Computational Units
226. NeurIPS 2026Position: We Need Greater Transparency to Maintain Research Pipeline Reliability Despite GenAI
227. NeurIPS 2026Positional Encoding and Prompt-Order Sensitivity in In-Context Learning
228. NeurIPS 2026PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers
229. NeurIPS 2026PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI
230. NeurIPS 2026Preconditioned Flow Matching
231. NeurIPS 2026Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints
232. NeurIPS 2026Predicting directional flexibility in proteins
233. NeurIPS 2026Prevailing Bisimulation Metric Learning Is Biased: Implicit Regularization and Its Remedy
234. NeurIPS 2026PRISM:Disentangling Preference Distributions for Generative Ranking
235. NeurIPS 2026Probability-Conserving Flow Guidance
236. NeurIPS 2026ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
237. NeurIPS 2026Projection Learning: A Principled Way to Overcome Memorization in Distribution Learning
238. NeurIPS 2026R-GRec: Relation-Guided Generative Recommendation via Collaborative Graph Supervision
239. NeurIPS 2026RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance
240. NeurIPS 2026RA-ClipScore: Making Generative Model Evaluation More Interpretable
241. NeurIPS 2026RadarMAE: Injecting Physical Inductive Biases into Masked Autoencoders for Advanced Radar Object Detection
242. NeurIPS 2026Rate-Constrained Edge Metadata for Sender–Receiver Generative Video Super-Resolution
243. NeurIPS 2026Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective
244. NeurIPS 2026Reasoning with Sampling: Cutting at Decision Points
245. NeurIPS 2026Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
246. NeurIPS 2026Reflected Schrödinger Bridge Matching
247. NeurIPS 2026Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow Models
248. NeurIPS 2026Relaxation-Aligned State Control for Test-Time Scaling in Generative Combinatorial Optimization
249. NeurIPS 2026Renoise Consistency: Unlocking Efficient Self-Correction for Diffusion Large Language Models
250. NeurIPS 2026Rethinking Knowledge Distillation for Diffusion Language Models

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.