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

604 papers, page 11 of 13

501. ICML 2026Statistical Consistency and Generalization of Contrastive Representation Learning
502. ICML 2026Steer Like the LLM: Activation Steering that Mimics Prompting
503. ICML 2026Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions
504. ICML 2026Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
505. ICML 2026Strategic Candidacy in Generative AI Arenas
506. ICML 2026StructMAR: Structure-Aware Masked Autoregression for Explicit Layout Alignment in Text-to-Image Generation
507. ICML 2026Structurally Aligned Subtask-Level Memory for Software Engineering Agents
508. ICML 2026Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
509. ICML 2026Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
510. ICML 2026SVRG and Beyond via Posterior Correction
511. ICML 2026Symbol-Equivariant Recurrent Reasoning Models
512. ICML 2026SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
513. ICML 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
514. ICML 2026TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling
515. ICML 2026Tail Annealing for Heavy-Tailed Flow Matching
516. ICML 2026Taming Aleatoric Impulse in Off-Policy Reinforcement Learning
517. ICML 2026Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance
518. ICML 2026Temperature Scaling in Discrete Sequence (Language) Models
519. ICML 2026Temporal Difference Learning for Diffusion Models
520. ICML 2026Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
521. ICML 2026Test-Time Anchoring for Discrete Diffusion Posterior Sampling
522. ICML 2026Test-Time Guidance for Flow-Based Generative Models via Parallel Tempering on Source Distributions
523. ICML 2026Test-Time Reinforcement Learning for Flow Matching
524. ICML 2026Text Generation as Continuous Latent Dynamics via Reinforcement Learning
525. ICML 2026The Accumulation of Score Estimation Error in Diffusion Models
526. ICML 2026The Convergent Representation of Contrastive Vision-Language Models: Geometry, Modality Gap and Shared Space Alignment
527. ICML 2026The Data Manifold under the Microscope
528. ICML 2026The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms
529. ICML 2026The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity
530. ICML 2026The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
531. ICML 2026The Velocity Deficit: Initial Energy Injection for Flow Matching
532. ICML 2026Thinking with Geometry: Active Geometry Integration for Spatial Reasoning
533. ICML 2026Threshold-Guided Optimization for Visual Generative Models
534. ICML 2026Tightening the Score Matching Gap for Diffusion Models
535. ICML 2026Tilt Matching for Scalable Sampling and Fine-Tuning
536. ICML 2026Time-Conditioned Foreseeing: An EHR-Specific Foundation Model for Irregular Dynamics and Calendrical Time
537. ICML 2026Timestep Rescheduling in Diffusion Inversion
538. ICML 2026TMD-Bench: A Multi-Level Evaluation Paradigm for Music–Dance Co-Generation
539. ICML 2026Toward Identifiable Sparse Autoencoders
540. ICML 2026Towards A Generative Protein Evolution Machine with DPLM-Evo
541. ICML 2026Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
542. ICML 2026Towards Generative Graph Matching for Graph Edit Distance Computation
543. ICML 2026Towards Spectroscopy: Susceptibility Clusters in Language Models
544. ICML 2026Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
545. ICML 2026Training-Free Adaptation of Diffusion Models via Doob's $h$-Transform
546. ICML 2026Training-Free Bayesian Filtering with Generative Emulators
547. ICML 2026Training-Free Rate-Distortion-Perception Traversal With Diffusion
548. ICML 2026Training-Free Vector Quantization via Gaussian VAEs
549. ICML 2026Trajectory Consistency for One-Step Generation on Euler Mean Flows
550. ICML 2026Trajectory Stitching for Solving Inverse Problems with Flow-Based 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.