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

1,714 papers, page 6 of 35

251. NeurIPS 2026Rethinking Memorization–Generalization Trade-Off in Generative Models
252. NeurIPS 2026Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
253. NeurIPS 2026Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment
254. NeurIPS 2026Rethinking Vector Field Learning for Generative Segmentation
255. NeurIPS 2026Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review
256. NeurIPS 2026Revisiting The Power of Closed-Form: Robust Deep Image Prototype Discovery via Scale Mixtures
257. NeurIPS 2026Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
258. NeurIPS 2026Reward Is Not a Universal Interface for Generative Reinforcement Learning
259. NeurIPS 2026Reweighted Flow Matching via Unbalanced Optimal Transport for Label-free Long-tailed Generation
260. NeurIPS 2026RGF: Recursive Generative Framework for the Edge-Cut Separable Problems
261. NeurIPS 2026Robust Flow Matching under Target Corruption and Label Noise
262. NeurIPS 2026Rotations on Latent Hyperspheres: a Geometry-Aware Guiding Framework for Diffusion Models
263. NeurIPS 2026Routing as a Singular Reparameterization: A Closed-Form Pushforward Prior and Exact Bayesian Complexity in a Minimal Proxy
264. NeurIPS 2026Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
265. NeurIPS 2026SAGE: Semantically Disentangled Representation Learning through Latent Geometry Constraint and Large Language Model
266. NeurIPS 2026Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders
267. NeurIPS 2026Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
268. NeurIPS 2026Sample-Efficient Optimization over Generative Priors via Coarse Learnability
269. NeurIPS 2026SARA: Step-Adaptive Rank Adjustment for Diffusion Inference Acceleration
270. NeurIPS 2026Scattered by Design: Why Per-Output Pruning Resists Structured Compression
271. NeurIPS 2026Seeing the Unseen: Unified Visible–Invisible Motion for Physically Consistent Video Generation
272. NeurIPS 2026Selective Safety Steering via Value-Filtered Decoding
273. NeurIPS 2026Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
274. NeurIPS 2026ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens
275. NeurIPS 2026SOLAR: AI-Powered Speed-of-Light Performance Analysis
276. NeurIPS 2026SP$^3$: Spherical Priors for Plug-and-Play Restoration
277. NeurIPS 2026Sparse Biological Features Reveal Early Functional Commitment in Diffusion Protein Language Models
278. NeurIPS 2026Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems
279. NeurIPS 2026Spectral-Sphere-Constrained Hyper-Connections
280. NeurIPS 2026Split-and-scale Latent 3D Representations
281. NeurIPS 2026Stability and Diversity of Networked Self-Consuming Generative Ecosystems
282. NeurIPS 2026Stable and Granular Policy Optimization for Generative Recommendation
283. NeurIPS 2026Stable GFlowNets with Probabilistic Guarantees
284. NeurIPS 2026Stein Transport for Generative Modeling
285. NeurIPS 2026StiCAS: Compositional Activation Steering via Stiefel Manifold Coordinate Transport
286. NeurIPS 2026Stochastic Heat Diffusion Models
287. NeurIPS 2026Stochastic Interpolants via Conditional Dependent Coupling
288. NeurIPS 2026Structural Rationale Distillation via Reasoning Space Compression
289. NeurIPS 2026Structured Coupling for Flow Matching
290. NeurIPS 2026Supervised Distributional Reduction via Optimal Transport and Dependence Maximization
291. NeurIPS 2026Support Before Frequency in Discrete Diffusion
292. NeurIPS 2026Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
293. NeurIPS 2026SVG-3D: Mining Decision Boundaries with Generative Splatting Priors for Zero-Shot 3D Classification
294. NeurIPS 2026SynMQG: Disentanglement and Mutual-Information Optimization for Synergistic Multi-modal Question Generation
295. NeurIPS 2026Tabular Foundation Model for Generative Modelling
296. NeurIPS 2026Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
297. NeurIPS 2026Taming Generative Co-Folding Prior for Molecular Docking with Diffusion Bridge
298. NeurIPS 2026Temporal Backtracking Search for Test-time Generative Video Reasoning
299. NeurIPS 2026Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models
300. NeurIPS 2026Temporal Pair Consistency for Flow Matching

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.