General ML · generalization papers, 2023–2026

Key findings

• General ML · generalization went from 136 papers in 2023 to 152 in 2026, roughly 1.1x in three years.
• NeurIPS publishes the most General ML · generalization work: 207 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Theory · learning theory: papers tagged with both rose from 3 in 2023 to 20 in 2026.
• Among the 6 topics under General Machine Learning, it ranks #5 by 2026 paper count; the fastest grower in the group, General ML · evaluation, is up 4.3x versus 1.1x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Asymmetric Generalization in Deep CTR Models: A Block-wise Diagnosis
• ICML 2026Anti-causal domain generalization: Leveraging unlabeled data
• ICLR 2026Generalization Below the Edge of Stability: The Role of Data Geometry
• CVPR 2026PriVi Towards a General-Purpose Video Model for Primate Behavior in
• NeurIPS 2025Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
• ICML 2025Causality Inspired Federated Learning for OOD Generalization
• ICLR 2025Federated Domain Generalization with Data-free On-server Matching Gradient
• CVPR 2025Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization
• NeurIPS 2024Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
• ICML 2024Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses
• ICLR 2024Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
• CVPR 2024Disentangled Prompt Representation for Domain Generalization
• NeurIPS 2023A unified framework for information-theoretic generalization bounds
• ICML 2023Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
• ICLR 2023ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations
• CVPR 2023AltFreezing for More General Video Face Forgery Detection
• NeurIPS 2026Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
• ICML 2026Are Object-Centric Representations Better at Compositional Generalization?
• ICLR 2026Temporal Generalization: A Reality Check
• CVPR 2026The Golden Subspace Where Efficiency Meets Generalization in Continual Test-Time

All General ML · generalization papers

592 papers, page 6 of 12

251. ICML 2025Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
252. ICML 2025Set Valued Predictions For Robust Domain Generalization
253. ICML 2025Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate
254. ICML 2025Stabilizing Sample Similarity in Representation via Mitigating Random Consistency
255. ICML 2025Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?
256. ICML 2025The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
257. ICML 2025Understanding Generalization in Quantum Machine Learning with Margins
258. ICML 2025Universal Length Generalization with Turing Programs
259. ICML 2025Weak-to-Strong Generalization Even in Random Feature Networks, Provably
260. ICML 2025Weight matrices compression based on PDB model in deep neural networks
261. NeurIPS 2025A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
262. NeurIPS 2025Adversarial generalization of unfolding (model-based) networks
263. NeurIPS 2025Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations
264. NeurIPS 2025An Effective Levelling Paradigm for Unlabeled Scenarios
265. NeurIPS 2025Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
266. NeurIPS 2025Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning
267. NeurIPS 2025Beyond Benign Overfitting in Nadaraya-Watson Interpolators
268. NeurIPS 2025Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
269. NeurIPS 2025Continuous Domain Generalization
270. NeurIPS 2025Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization
271. NeurIPS 2025Extrapolation by Association: Length Generalization Transfer In Transformers
272. NeurIPS 2025Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
273. NeurIPS 2025From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
274. NeurIPS 2025Generalization Bounds for Model-based Algorithm Configuration
275. NeurIPS 2025Generalization Bounds for Rank-sparse Neural Networks
276. NeurIPS 2025Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
277. NeurIPS 2025Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming
278. NeurIPS 2025Generalization vs Specialization under Concept Shift
279. NeurIPS 2025Generalizing Verifiable Instruction Following
280. NeurIPS 2025Generalizing while preserving monotonicity in comparison-based preference learning models
281. NeurIPS 2025Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
282. NeurIPS 2025HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
283. NeurIPS 2025How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning
284. NeurIPS 2025How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
285. NeurIPS 2025How Patterns Dictate Learnability in Sequential Data
286. NeurIPS 2025Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables
287. NeurIPS 2025Is Grokking a Computational Glass Relaxation?
288. NeurIPS 2025Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence
289. NeurIPS 2025Learning Robust Spectral Dynamics for Temporal Domain Generalization
290. NeurIPS 2025Learning to Generalize: An Information Perspective on Neural Processes
291. NeurIPS 2025Length Generalization via Auxiliary Tasks
292. NeurIPS 2025Less is More: Local Intrinsic Dimensions of Contextual Language Models
293. NeurIPS 2025Linear Transformers Implicitly Discover Unified Numerical Algorithms
294. NeurIPS 2025Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective
295. NeurIPS 2025Mamba Modulation: On the Length Generalization of Mamba Models
296. NeurIPS 2025Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization
297. NeurIPS 2025Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
298. NeurIPS 2025On Inductive Biases That Enable Generalization in Diffusion Transformers
299. NeurIPS 2025On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
300. NeurIPS 2025On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective

FAQ

How many General ML · generalization papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

592 in total: 136 in 2023, 135 in 2024, 169 in 2025, 152 in 2026.

How many General ML · generalization papers are at NeurIPS 2026?

NeurIPS 2026 has 58 General ML · generalization papers, versus 61 the year before.

How many General ML · generalization papers are at ICLR 2026?

ICLR 2026 has 38 General ML · generalization papers, versus 33 the year before.

How many General ML · generalization papers are at ICML 2026?

ICML 2026 has 47 General ML · generalization papers, versus 61 the year before.

How many General ML · generalization papers are at CVPR 2026?

CVPR 2026 has 9 General ML · generalization papers, versus 14 the year before.

Which conference publishes the most General ML · generalization papers?

NeurIPS, with 207 papers from 2023 to 2026.