Sim-to-Real papers, 2023–2026

Key findings

• Sim-to-Real went from 159 papers in 2023 to 204 in 2026, roughly 1.3x in three years.
• CVPR publishes the most Sim-to-Real work: 223 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 2 in 2023 to 27 in 2026.
• Among the 5 topics under Robotics and Embodied AI, it ranks #3 by 2026 paper count; the fastest grower in the group, Humanoid Control, is up 3.8x versus 1.3x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026AET-Bench: Pixel-Accurate Atomic Tomography Is Not Atom-Accurate
• ICML 2026RTInfer: Real-Time Inference of Multiple DNNs on Edge GPUs
• ICLR 2026Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots
• CVPR 2026AnthroTAP Learning Point Tracking with Real-World Motion
• NeurIPS 2025Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models
• ICML 2025HyperIV: Real-time Implied Volatility Smoothing
• ICLR 2025Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale Benchmark
• CVPR 2025Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation
• NeurIPS 2024EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity
• ICML 2024A Global Geometric Analysis of Maximal Coding Rate Reduction
• ICLR 2024Extending Power of Nature from Binary to Real-Valued Graph Learning in Real World
• CVPR 2024Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds
• NeurIPS 2023[Re] Pure Noise to the Rescue of Insufficient Data
• ICML 2023Adversarially Robust PAC Learnability of Real-Valued Functions
• ICLR 2023Provable Sim-to-real Transfer in Continuous Domain with Partial Observations
• CVPR 2023Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-World
• NeurIPS 2026Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes
• ICML 2026Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer
• ICLR 2026PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation
• CVPR 2026BiProLoRA Bilevel Prompt LoRA for Real Scene Recovery

All Sim-to-Real papers

120 papers, page 3 of 3

101. ICML 2023Federated Heavy Hitter Recovery under Linear Sketching
102. ICML 2023Formalizing Preferences Over Runtime Distributions
103. ICML 2023From Perception to Programs: Regularize, Overparameterize, and Amortize
104. ICML 2023From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks
105. ICML 2023Identifiability of Label Noise Transition Matrix
106. ICML 2023Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
107. ICML 2023Multi-Environment Pretraining Enables Transfer to Action Limited Datasets
108. ICML 2023Multiplier Bootstrap-based Exploration
109. ICML 2023Never mind the metrics---what about the uncertainty? Visualising binary confusion matrix metric distributions to put performance in perspective
110. ICML 2023On the Robustness of Randomized Ensembles to Adversarial Perturbations
111. ICML 2023One-sided Matrix Completion from Two Observations Per Row
112. ICML 2023Out-of-Domain Robustness via Targeted Augmentations
113. ICML 2023Regret Minimization and Convergence to Equilibria in General-sum Markov Games
114. ICML 2023Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization
115. ICML 2023Robust Budget Pacing with a Single Sample
116. ICML 2023Safe Offline Reinforcement Learning with Real-Time Budget Constraints
117. ICML 2023Settling the Reward Hypothesis
118. ICML 2023Stable Estimation of Heterogeneous Treatment Effects
119. ICML 2023Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic Data
120. ICML 2023Vector-Valued Control Variates

FAQ

How many Sim-to-Real papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

629 in total: 159 in 2023, 148 in 2024, 118 in 2025, 204 in 2026.

How many Sim-to-Real papers are at NeurIPS 2026?

NeurIPS 2026 has 75 Sim-to-Real papers, versus 33 the year before.

How many Sim-to-Real papers are at ICLR 2026?

ICLR 2026 has 33 Sim-to-Real papers, versus 16 the year before.

How many Sim-to-Real papers are at ICML 2026?

ICML 2026 has 33 Sim-to-Real papers, versus 18 the year before.

How many Sim-to-Real papers are at CVPR 2026?

CVPR 2026 has 63 Sim-to-Real papers, versus 51 the year before.

Which conference publishes the most Sim-to-Real papers?

CVPR, with 223 papers from 2023 to 2026.