Core AI
68,648 papers (13 classified directly here)
Subtopics · a paper can sit in several, so these overlap
Multimodal Learning (14,926)
Large Language Models (9,515)
Interpretability (8,292)
Foundation Models (5,277)
Agent Systems (4,710)
Causal Inference (3,958)
Multi-Agent Systems (3,842)
AI Safety (3,602)
Planning (3,482)
Reasoning (3,360)
Human-AI Interaction (2,465)
Model Compression (2,258)
Natural Language Processing (2,186)
Responsible AI (2,130)
Computer Vision (1,901)
Game AI (1,846)
Reinforcement Learning (1,699)
Adversarial Learning (1,500)
Autonomous Vehicles (1,488)
Language (1,345)
Fairness (1,279)
Game Theory (1,129)
Robotics (1,087)
Dialogue Systems (1,066)
Efficient Computing (956)
Vision-Language Models (930)
Knowledge Graph (735)
Procedural Generation (709)
Trajectory Prediction (676)
Evaluation (655)
Privacy (617)
Natural Language Generation (573)
Information Retrieval (541)
Memory (526)
Decision Making (480)
Safety (474)
Knowledge Representation (409)
Knowledge (386)
Information Extraction (378)
Speech Processing (310)
Knowledge Graphs (282)
Security (256)
Uncertainty Quantification (246)
Representation Learning (239)
Retrieval-Augmented Generation (225)
Knowledge Editing (200)
Question Answering (199)
Attention (198)
Robustness (186)
Knowledge Distillation (185)
Code Generation (168)
Explainability (142)
Brain-Computer Interface (141)
Neural Networks (136)
Anomaly Detection (132)
Automated Reasoning (84)
Natural Language Understanding (81)
Multi-Lingual Learning (79)
Education (64)
Machine Translation (57)
Learning Paradigms (57)
Speech Recognition (55)
Risk Management (51)
Visual Question Answering (49)
Communication (35)
Motion Analysis (32)
Natural Language Inference (29)
Sentiment Analysis (19)
Representation (17)
Papers per year
1
4
10
1
11
82
89
98
89
99
120
153
269
217
273
416
1,053
1,809
3,137
4,063
4,997
5,940
7,896
12,509
17,181
8,131
2000
'5
'10
'15
'20
'25
Papers (including subtopics)
Language Modeling Is Compression
ICLR 2024
Language Model Inversion
ICLR 2024
Language models and brains align due to more than next-word prediction and word-level information
EMNLP 2024
Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain
NAACL 2024
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
ACL 2024
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
ICML 2024
Language Models as Black-Box Optimizers for Vision-Language Models
CVPR 2024
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
EMNLP 2024
Language Models as Inductive Reasoners
EACL 2024
Language Models as Science Tutors
ICML 2024
Language Models can Evaluate Themselves via Probability Discrepancy
ACL 2024
Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks
ACL 2024
Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
ACL 2024
Language Models Don’t Learn the Physical Manifestation of Language
ACL 2024
Language Models Implement Simple Word2Vec-style Vector Arithmetic
NAACL 2024
Language Models in Dialogue: Conversational Maxims for Human-AI Interactions
EMNLP 2024
Language Models Linearly Represent Sentiment
EMNLP 2024
Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion
NAACL 2024
Language Models Represent Beliefs of Self and Others
ICML 2024
Language Models Represent Space and Time
ICLR 2024
Language Models Still Struggle to Zero-shot Reason about Time Series
EMNLP 2024
Language Models with Conformal Factuality Guarantees
ICML 2024
Language + Molecules
EACL 2024
Language, OCR, Form Independent (LOFI) pipeline for Industrial Document Information Extraction
EMNLP 2024
Language-only Training of Zero-shot Composed Image Retrieval
CVPR 2024