Learning Types
56,253 papers (3 classified directly here)
Subtopics · a paper can sit in several, so these overlap
Self-Supervised Learning (8,965)
Adversarial Learning (5,204)
Unsupervised Learning (4,874)
Transfer Learning (4,808)
Weakly Supervised Learning (3,938)
Contrastive Learning (3,748)
Zero-Shot Learning (3,130)
Semi-Supervised Learning (3,128)
Reinforcement Learning (3,118)
Multi-Task Learning (2,556)
Evaluation (2,164)
Continual Learning (2,107)
Active Learning (1,983)
Few-Shot Learning (1,840)
Deep Learning (1,404)
Online Learning (1,360)
Multi-Armed Bandits (1,327)
Multimodal Learning (1,289)
Supervised Learning (986)
Multi-Agent Systems (813)
Uncertainty Quantification (805)
Causal Inference (636)
Robustness (576)
Retrieval-Augmented Generation (565)
Fine-Tuning (490)
Ensemble Learning (482)
In-Context Learning (439)
Multi-Label Classification (430)
Imitation Learning (387)
Prompt Engineering (270)
Multi-Lingual Learning (269)
Distribution Shift (264)
Reinforcement Learning from Human Feedback (209)
Regularization (207)
Exploration-Exploitation (203)
Generative Models (200)
Multi-Objective Optimization (185)
Out-of-Distribution Detection (176)
Sparse Learning (165)
Sampling (150)
Preference Learning (136)
Offline Reinforcement Learning (130)
Multi-Label Learning (128)
Markov Decision Process (127)
Neural Architecture Search (122)
Multi-Instance Learning (121)
Multi-View Learning (117)
Robust Learning (110)
Generative Model (110)
Time Series (108)
Large Language Models (104)
Exploration (103)
Hyperparameter Optimization (99)
Machine Unlearning (95)
Imbalanced Learning (93)
Machine Translation (93)
Multi-Class Classification (85)
Differential Privacy (82)
Time Series Analysis (71)
Reasoning (70)
Calibration (67)
Structure Learning (66)
Physics-Informed Learning (62)
Class Imbalance (58)
Model-Based RL (55)
Interactive Learning (55)
Multi-Domain Learning (47)
Inverse Reinforcement Learning (46)
Crowdsourcing (40)
Off-Policy Learning (38)
Label Noise (38)
Noisy Label Learning (35)
Offline RL (32)
Attention (32)
Evolutionary Algorithm (32)
Decision Making (31)
Policy Learning (30)
Personalization (28)
Low-Resource Learning (26)
Collaborative Filtering (25)
Self-Training (24)
Sequential Modeling (24)
Parameter Estimation (23)
Survival Analysis (21)
Machine Learning (20)
Parameter-Efficient Fine-Tuning (20)
Synthetic Data Generation (20)
Annotation (18)
Symbolic Regression (18)
AutoML (16)
Security (15)
Multi-Source Learning (13)
Distant Supervision (13)
Text Generation (11)
Distributional Reinforcement Learning (9)
Sentiment Analysis (9)
Multi-Hop Reasoning (9)
Language Modeling (9)
Code Generation (8)
Multi-Object Tracking (8)
Natural Language Inference (7)
Chain-of-Thought (6)
Question Answering (5)
Papers per year
1
8
12
26
18
20
135
136
147
149
220
231
316
526
460
477
660
1,314
2,083
3,689
4,652
5,914
6,826
8,201
8,755
9,258
2,019
2000
'5
'10
'15
'20
'25
Papers (including subtopics)
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood
ACL 2026
To make someone do something: mining alert-style directives in Bulgarian social media for low-resource language modelling
EACL 2026
ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool learning
AAAI 2026
To Paraphrase or Not: Efficient Comment Detoxification with Unsupervised Detoxifiability Discrimination
EACL 2026
TopoCL: Topological Contrastive Learning for Medical Imaging
CVPR 2026
Topology-aware Knowledge Preservation for Class-Incremental Learning
AAAI 2026
Topology-Inspired Backward-Free Framework for Test-Time Adaptation in Medical Detection
AAAI 2026
TOSC: Task-Oriented Shape Completion for Open-World Dexterous Grasp Generation from Partial Point Clouds
AAAI 2026
Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance
AAAI 2026
Toward Causal Foundation World Models: From Representation to Decision-Making
AAAI 2026
Toward Gaze Target Detection of Young Autistic Children
AAAI 2026
Towards Adaptive Humanoid Control via Multi-Behavior Distillation and Reinforced Fine-Tuning
AAAI 2026
Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detection (Abstract Reprint)
AAAI 2026
Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning
AAAI 2026
Towards Better Correctness and Efficiency in Code Generation
AAAI 2026
Towards Calibrating Prompt Tuning of Vision- Language Models
CVPR 2026
Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios
AAAI 2026
Towards Continually-Evolving AI: Selective and Expandable Multimodal Memory System
AAAI 2026
Towards Distance-Invariant Radio Frequency Fingerprinting via Augmented Unsupervised Learning
AAAI 2026
Towards Effective Code-Integrated Reasoning
AAAI 2026
Towards Egocentric 3D Hand Pose Estimation in Unseen Domains
WACV 2026
Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation
WACV 2026
Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
CVPR 2026
Toward Simultaneously Optimal Regret in U-Calibration
COLT 2026
Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space
AAAI 2026