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 25 of 87

1201. NeurIPS 2026Generalization Dynamics of Linear Diffusion Models
1202. NeurIPS 2026Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
1203. NeurIPS 2026Generating Financial Time Series by Matching Random Convolutional Features
1204. NeurIPS 2026Generative Active Learning via Bayesian Acquisition for Improving the Efficiency of Synthetic Data
1205. NeurIPS 2026Generative Actor-Critic with Soft Bridge Policies
1206. NeurIPS 2026Generative Conformal Prediction with Optimized Coverage Allocation
1207. NeurIPS 2026Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification
1208. NeurIPS 2026Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows
1209. NeurIPS 2026Generative Modeling via Drifting
1210. NeurIPS 2026Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport
1211. NeurIPS 2026GenRec: Knowing Where to Reconstruct and Where to Generate
1212. NeurIPS 2026GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
1213. NeurIPS 2026Geometric Velocity Regularity for Flow Matching on Manifold-Concentrated Data
1214. NeurIPS 2026gfnx: Fast and Scalable Library for Generative Flow Networks in JAX
1215. NeurIPS 2026GPA: Generative Population Annealing for Test-Time Sequence Design with Pretrained Generative Models
1216. NeurIPS 2026Gradient Routing Localizes and Removes Unintended Behaviors in RL
1217. NeurIPS 2026Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
1218. NeurIPS 2026HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields
1219. NeurIPS 2026HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
1220. NeurIPS 2026Hit Expansion via Localized Exploration of Synthesizable Chemical Space
1221. NeurIPS 2026Horizontal Diffusion Models: Score-based Generative Modeling on Frame-Connection Geometry
1222. NeurIPS 2026Hypergraph Generation via Structured Stochastic Diffusion
1223. NeurIPS 2026HyperTransport: Amortized Conditioning of T2I Generative Models
1224. NeurIPS 2026HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression
1225. NeurIPS 2026Idempotency Exposes Consistency Problems in Sparse Autoencoders
1226. NeurIPS 2026Imagine, Don't Narrate: The Generative Bottleneck in World Models of Interaction Dynamics
1227. NeurIPS 2026Improving Function Space Flow Matching with Kernel Optimal Transport
1228. NeurIPS 2026Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
1229. NeurIPS 2026Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion
1230. NeurIPS 2026Inference-Time Self-Aligned Drifting for Few-Step Flow Matching
1231. NeurIPS 2026Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream
1232. NeurIPS 2026Inferring how internal brain state shapes neural responses with state-dependent diffusion models
1233. NeurIPS 2026Information-Geometric Forward Policy Training in GFlowNets
1234. NeurIPS 2026Invariance and Body-Order Compose Additively: Minimax Rates on $\mathrm{SO}(3)^n$
1235. NeurIPS 2026Is a Linear Probe Evidence of a Linear Representation?
1236. NeurIPS 2026Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
1237. NeurIPS 2026JaSpec-LID: Local Intrinsic Dimension Estimation via Jacobian Spectra of ODE-based Generative Models
1238. NeurIPS 2026Kernel-Gradient Drifting Models
1239. NeurIPS 2026Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting
1240. NeurIPS 2026Latent Process Generator Matching
1241. NeurIPS 2026LayoutBridge: Anisotropic Brownian Bridges for Public Indoor Floorplan Generation
1242. NeurIPS 2026Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
1243. NeurIPS 2026Learn from your own latents and not from tokens: A sample-complexity theory
1244. NeurIPS 2026Learning a Unified Cross-Model Semantic Dictionary via Gated Bottleneck Sparse Autoencoders
1245. NeurIPS 2026Learning Distributions from Multiple Data Providers
1246. NeurIPS 2026Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints
1247. NeurIPS 2026Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
1248. NeurIPS 2026Learning to Solve Generative ODEs Beyond the Linear Span
1249. NeurIPS 2026Less is More: Fewer Tokens and Blocks Make AIGI Detection Faster and More Generalizable
1250. NeurIPS 2026Likelihood-Free Generative Policy Optimization

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.