General ML · unsupervised and semisupervised learning papers, 2023–2026

Key findings

• General ML · unsupervised and semisupervised learning went from 649 papers in 2023 to 799 in 2026, roughly 1.2x in three years.
• ICML publishes the most General ML · unsupervised and semisupervised learning work: 859 papers from 2023 to 2026, 32% of the four-venue total.
• The fastest-growing overlap is with Deep learning · self supervised learning: papers tagged with both rose from 23 in 2023 to 86 in 2026.
• Among the 6 topics under General Machine Learning, it ranks #1 by 2026 paper count; the fastest grower in the group, General ML · evaluation, is up 4.3x versus 1.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A general kernel framework for non-CND distance measures using $|\mathcal{D}|$-dimensional sparse landmark embeddings
• ICML 2026$\mu$pscaling small models: Principled warm starts and hyperparameter transfer
• ICLR 2026A Generalized Geometric Theoretical Framework of Centroid Discriminant Analysis for Linear Classification of Multi-dimensional Data
• CVPR 2026COG Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object
• NeurIPS 2025$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
• ICML 2025A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning
• ICLR 2025A General Framework for Producing Interpretable Semantic Text Embeddings
• CVPR 2025A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpening
• NeurIPS 2024GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
• ICML 2024CKGConv: General Graph Convolution with Continuous Kernels
• ICLR 2024A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
• CVPR 2024Dual Prototype Attention for Unsupervised Video Object Segmentation
• NeurIPS 2023$H$-Consistency Bounds: Characterization and Extensions
• ICML 2023A Mathematical Model for Curriculum Learning for Parities
• ICLR 2023A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
• CVPR 2023A General Regret Bound of Preconditioned Gradient Method for DNN Training
• NeurIPS 2026Attention-based PCA
• ICML 2026A Control-Theoretic View of Mamba on Stability and Robustness
• ICLR 2026A Single Architecture for Representing Invariance Under Any Space Group
• CVPR 2026CROWn A Unified Framework for Anti-Aliased Downsampling and Phase-Calibrated Fusion

All General ML · unsupervised and semisupervised learning papers

682 papers, page 13 of 14

601. NeurIPS 2025OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction
602. NeurIPS 2025On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
603. NeurIPS 2025On the Hardness of Conditional Independence Testing In Practice
604. NeurIPS 2025On the Loss of Context Awareness in General Instruction Fine-tuning
605. NeurIPS 2025On the Relation between Rectified Flows and Optimal Transport
606. NeurIPS 2025Online Learning of Pure States is as Hard as Mixed States
607. NeurIPS 2025Optimal Graph Clustering without Edge Density Signals
608. NeurIPS 2025Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
609. NeurIPS 2025Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
610. NeurIPS 2025Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
611. NeurIPS 2025Parameter Dynamics of Online Machine Learning and Test-time Adaptation
612. NeurIPS 2025Precise Asymptotics and Refined Regret of Variance-Aware UCB
613. NeurIPS 2025Preference Learning with Response Time: Robust Losses and Guarantees
614. NeurIPS 2025Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization
615. NeurIPS 2025RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation
616. NeurIPS 2025Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
617. NeurIPS 2025Restoring Pruned Large Language Models via Lost Component Compensation
618. NeurIPS 2025Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning
619. NeurIPS 2025Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics
620. NeurIPS 2025Rethinking PCA Through Duality
621. NeurIPS 2025RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees
622. NeurIPS 2025Robust Label Proportions Learning
623. NeurIPS 2025Robust Regression of General ReLUs with Queries
624. NeurIPS 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
625. NeurIPS 2025RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality
626. NeurIPS 2025Sampled Estimators For Softmax Must Be Biased
627. NeurIPS 2025Scalable and adaptive prediction bands with kernel sum-of-squares
628. NeurIPS 2025Scalable Signature Kernel Computations via Local Neumann Series Expansions
629. NeurIPS 2025Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
630. NeurIPS 2025Separating the 'what' and 'how' of compositional computation to enable reuse and continual learning
631. NeurIPS 2025Shapley-Based Data Valuation for Weighted $k$-Nearest Neighbors
632. NeurIPS 2025SHGR: A Generalized Maximal Correlation Coefficient
633. NeurIPS 2025SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
634. NeurIPS 2025SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration
635. NeurIPS 2025Spatiotemporal Consensus with Scene Prior for Unsupervised Domain Adaptive Person Search
636. NeurIPS 2025Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold
637. NeurIPS 2025SPFL: Sequential updates with Parallel aggregation for Enhanced Federated Learning under Category and Domain Shifts
638. NeurIPS 2025SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding
639. NeurIPS 2025Split conformal classification with unsupervised calibration
640. NeurIPS 2025Stability and Oracle Inequalities for Optimal Transport Maps between General Distributions
641. NeurIPS 2025Stochastic Forward-Forward Learning through Representational Dimensionality Compression
642. NeurIPS 2025Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
643. NeurIPS 2025Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
644. NeurIPS 2025Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes
645. NeurIPS 2025The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
646. NeurIPS 2025Theoretical Insights into In-context Learning with Unlabeled Data
647. NeurIPS 2025Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining
648. NeurIPS 2025Tightening Regret Lower and Upper Bounds in Restless Rising Bandits
649. NeurIPS 2025Token Perturbation Guidance for Diffusion Models
650. NeurIPS 2025Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds

FAQ

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

2,683 in total: 649 in 2023, 553 in 2024, 682 in 2025, 799 in 2026.

How many General ML · unsupervised and semisupervised learning papers are at NeurIPS 2026?

NeurIPS 2026 has 194 General ML · unsupervised and semisupervised learning papers, versus 203 the year before.

How many General ML · unsupervised and semisupervised learning papers are at ICLR 2026?

ICLR 2026 has 187 General ML · unsupervised and semisupervised learning papers, versus 174 the year before.

How many General ML · unsupervised and semisupervised learning papers are at ICML 2026?

ICML 2026 has 348 General ML · unsupervised and semisupervised learning papers, versus 239 the year before.

How many General ML · unsupervised and semisupervised learning papers are at CVPR 2026?

CVPR 2026 has 70 General ML · unsupervised and semisupervised learning papers, versus 66 the year before.

Which conference publishes the most General ML · unsupervised and semisupervised learning papers?

ICML, with 859 papers from 2023 to 2026.