Browse State-of-the-Art › Knowledge Base
Knowledge Base
Benchmarks are leaderboard tables with at least one row whose task is in this area, counted by the task's area and not by the archive's per-table category tag, which agrees here; datasets are those the archive tags with a task in this area; papers with code are catalogue papers tagged with a task in this area that list at least one repository. Task images are not shown (the archive's image host no longer serves them).
Parent tasks
23 tasks in Knowledge Base have sub-tasks in the archive's task tree, most benchmarks first, then most papers with code. Each section shows up to 5 sub-tasks; the task page lists them all.
- Recommendation Systems (11)
- Text Summarization (12)
- Mathematical Reasoning (7)
- Entity Alignment (1)
- 2D Human Pose Estimation (6)
- Knowledge Graph Completion (4)
- Knowledge Graphs (5)
- Causal Inference (3)
- 10-shot image generation (21)
- 3D Absolute Human Pose Estimation (4)
- Reinforcement Learning (RL) (6)
- Breast Cancer Histology Image Classification (2)
- Mathematical Question Answering (1)
- Explainable Artificial Intelligence (XAI) (1)
- Knowledge Graph Embedding (1)
- 1 Image, 2*2 Stitchi (12)
- Large Language Model (3)
- Symbolic Regression (1)
- Data Integration (3)
- Table annotation (6)
- Literature Mining (1)
- 3D (38)
- Cancer (10)
Recommendation Systems
55 benchmarks · 1,997 papers with codeSequential Recommendation
13 benchmarks · 300 papers with code
Session-Based Recommendations
7 benchmarks · 84 papers with code
Multimodal Recommendation
5 benchmarks · 33 papers with code
Multi-Media Recommendation
4 benchmarks · 2 papers with code
Multi-modal Recommendation
3 benchmarks · 18 papers with code
5 shown of 11 sub-tasks (1 filed under another area). All sub-tasks of Recommendation Systems →
Text Summarization
37 benchmarks · 440 papers with codeAbstractive Text Summarization
15 benchmarks · 362 papers with code
Document Summarization
7 benchmarks · 226 papers with code
Multi-Document Summarization
5 benchmarks · 113 papers with code
Extractive Text Summarization
5 benchmarks · 34 papers with code
Long-Form Narrative Summarization
4 benchmarks · 4 papers with code
5 shown of 12 sub-tasks (6 filed under another area). All sub-tasks of Text Summarization →
Mathematical Reasoning
10 benchmarks · 395 papers with codeMath Word Problem Solving
13 benchmarks · 80 papers with code
Formal Logic
1 benchmark · 20 papers with code
Abstract Algebra
1 benchmark · 6 papers with code
Mathematical Induction
1 benchmark · 4 papers with code
High School Mathematics
1 benchmark · 1 paper with code
5 shown of 7 sub-tasks (2 filed under another area). All sub-tasks of Mathematical Reasoning →
Entity Alignment
10 benchmarks · 117 papers with codeMulti-modal Entity Alignment
8 benchmarks · 14 papers with code
1 shown of 1 sub-task.
2D Human Pose Estimation
10 benchmarks · 68 papers with codeAction Anticipation
8 benchmarks · 49 papers with code
Style Transfer
3 benchmarks · 759 papers with code
3D Face Animation
3 benchmarks · 25 papers with code
Community Question Answering
2 benchmarks · 50 papers with code
Semi-Supervised Human Pose Estimation
2 benchmarks · 3 papers with code
5 shown of 6 sub-tasks (3 filed under another area). All sub-tasks of 2D Human Pose Estimation →
Knowledge Graph Completion
7 benchmarks · 251 papers with codeInductive knowledge graph completion
3 benchmarks · 14 papers with code
Triple Classification
1 benchmark · 23 papers with code
Large Language Model
0 benchmarks · 2,250 papers with code
Inductive Relation Prediction
0 benchmarks · 11 papers with code
4 shown of 4 sub-tasks (2 filed under another area).
Knowledge Graphs
4 benchmarks · 1,273 papers with codeKnowledge Graph Completion
7 benchmarks · 251 papers with code
Complex Query Answering
6 benchmarks · 22 papers with code
Open Knowledge Graph Canonicalization
1 benchmark · 2 papers with code
Person-Centric Knowledge Graphs
0 benchmarks · 1 paper with code
Relational Pattern Learning
0 benchmarks · 1 paper with code
5 shown of 5 sub-tasks.
Causal Inference
3 benchmarks · 575 papers with codeHeterogeneous Treatment Effect Estimation
1 benchmark · 19 papers with code
Counterfactual Inference
0 benchmarks · 64 papers with code
IHDP-CATE
0 benchmarks · 0 papers with code
3 shown of 3 sub-tasks.
10-shot image generation
3 benchmarks · 21 papers with codeSemantic Segmentation
150 benchmarks · 6,644 papers with code
Text-to-Image Generation
17 benchmarks · 546 papers with code
Deblurring
17 benchmarks · 424 papers with code
Motion Synthesis
13 benchmarks · 126 papers with code
Image Deblurring
9 benchmarks · 167 papers with code
5 shown of 21 sub-tasks (15 filed under another area). All sub-tasks of 10-shot image generation →
3D Absolute Human Pose Estimation
3 benchmarks · 9 papers with code3D Face Animation
3 benchmarks · 25 papers with code
3D Human Shape Estimation
2 benchmarks · 19 papers with code
Image to 3D
0 benchmarks · 54 papers with code
Text-to-Face Generation
0 benchmarks · 5 papers with code
4 shown of 4 sub-tasks (3 filed under another area).
Reinforcement Learning (RL)
2 benchmarks · 4,749 papers with code3D Point Cloud Reinforcement Learning
1 benchmark · 2 papers with code
RoomEnv-v0
1 benchmark · 1 paper with code
RoomEnv-v1
1 benchmark · 1 paper with code
RoomEnv-v2
1 benchmark · 1 paper with code
Off-policy evaluation
0 benchmarks · 102 papers with code
5 shown of 6 sub-tasks. All sub-tasks of Reinforcement Learning (RL) →
Breast Cancer Histology Image Classification
2 benchmarks · 12 papers with codeBreast Cancer Detection
4 benchmarks · 40 papers with code
Breast Cancer Histology Image Classification (20% labels)
1 benchmark · 1 paper with code
2 shown of 2 sub-tasks.
Mathematical Question Answering
2 benchmarks · 9 papers with codeMath Word Problem Solving
13 benchmarks · 80 papers with code
1 shown of 1 sub-task (1 filed under another area).
Explainable Artificial Intelligence (XAI)
1 benchmark · 296 papers with codeSlice Discovery
0 benchmarks · 6 papers with code
1 shown of 1 sub-task.
Knowledge Graph Embedding
1 benchmark · 220 papers with codeOpen Knowledge Graph Embedding
0 benchmarks · 1 paper with code
1 shown of 1 sub-task.
1 Image, 2*2 Stitchi
1 benchmark · 3 papers with codePose Estimation
31 benchmarks · 1,679 papers with code
Text-to-Image Generation
17 benchmarks · 546 papers with code
Image Deblurring
9 benchmarks · 167 papers with code
Virtual Try-on
9 benchmarks · 114 papers with code
Style Transfer
3 benchmarks · 759 papers with code
5 shown of 12 sub-tasks (10 filed under another area). All sub-tasks of 1 Image, 2*2 Stitchi →
Large Language Model
0 benchmarks · 2,250 papers with codeKnowledge Graphs
4 benchmarks · 1,273 papers with code
RAG
1 benchmark · 758 papers with code
AI Agent
0 benchmarks · 111 papers with code
3 shown of 3 sub-tasks (1 filed under another area).
Symbolic Regression
0 benchmarks · 155 papers with codeEquation Discovery
0 benchmarks · 34 papers with code
1 shown of 1 sub-task.
Data Integration
0 benchmarks · 130 papers with codeEntity Resolution
11 benchmarks · 55 papers with code
Entity Alignment
10 benchmarks · 117 papers with code
Table annotation
0 benchmarks · 23 papers with code
3 shown of 3 sub-tasks (1 filed under another area).
Table annotation
0 benchmarks · 23 papers with codeColumn Type Annotation
12 benchmarks · 19 papers with code
Cell Entity Annotation
5 benchmarks · 6 papers with code
Columns Property Annotation
4 benchmarks · 5 papers with code
Row Annotation
1 benchmark · 1 paper with code
Table Type Detection
1 benchmark · 1 paper with code
5 shown of 6 sub-tasks. All sub-tasks of Table annotation →
Literature Mining
0 benchmarks · 7 papers with codeSystematic Literature Review
0 benchmarks · 49 papers with code
1 shown of 1 sub-task.
3D
0 benchmarks · 0 papers with codeObject Detection
123 benchmarks · 4,657 papers with code
Pose Estimation
31 benchmarks · 1,679 papers with code
Depth Estimation
14 benchmarks · 1,029 papers with code
3D Reconstruction
10 benchmarks · 793 papers with code
3D Face Reconstruction
9 benchmarks · 83 papers with code
5 shown of 38 sub-tasks (20 filed under another area). All sub-tasks of 3D →
Cancer
0 benchmarks · 0 papers with codeBreast Cancer Detection
4 benchmarks · 40 papers with code
Lung Cancer Diagnosis
2 benchmarks · 16 papers with code
Breast Cancer Histology Image Classification
2 benchmarks · 12 papers with code
Skin Cancer Classification
1 benchmark · 15 papers with code
Classification Of Breast Cancer Histology Images
0 benchmarks · 5 papers with code
5 shown of 10 sub-tasks. All sub-tasks of Cancer →
Tasks with no parent task
24 tasks in Knowledge Base sit at the top of the archive's task tree with no sub-tasks of their own, most benchmarks first, then most papers with code.
Multi-hop Question Answering
2 benchmarks · 92 papers with code
MMLU
1 benchmark · 156 papers with code
Knowledge Base Population
1 benchmark · 32 papers with code
Causal Discovery
0 benchmarks · 294 papers with code
TruthfulQA
0 benchmarks · 37 papers with code
Probabilistic Deep Learning
0 benchmarks · 34 papers with code
Knowledge Base Construction
0 benchmarks · 28 papers with code
Temporal Knowledge Graph Completion
0 benchmarks · 22 papers with code
Non-Intrusive Load Monitoring
0 benchmarks · 18 papers with code
Multi-modal Knowledge Graph
0 benchmarks · 15 papers with code
Ontology Embedding
0 benchmarks · 15 papers with code
User Identification
0 benchmarks · 15 papers with code
Linear Mode Connectivity
0 benchmarks · 14 papers with code
Ontology Matching
0 benchmarks · 14 papers with code
Models Alignment
0 benchmarks · 6 papers with code
Knowledge Graphs Data Curation
0 benchmarks · 4 papers with code
Re-basin
0 benchmarks · 4 papers with code
Text2Sparql
0 benchmarks · 3 papers with code
Commonsense Knowledge Base Construction
0 benchmarks · 2 papers with code
RDF Dataset Discovery
0 benchmarks · 2 papers with code
Citation Visualization
0 benchmarks · 1 paper with code
Manufacturing simulation
0 benchmarks · 1 paper with code
Ontology Subsumption Inferece
0 benchmarks · 1 paper with code
Temporal Complex Logical Reasoning
0 benchmarks · 0 papers with code
1 task in Knowledge Base is filed only under a parent task from another area and is not listed on this page; the parent's task page carries it.
The archive's category table says 136 tasks; 134 task rows carry this area name.
Task tree and counts are the archive's, frozen 2025-07-28 archive 2025-07-28. Nothing here is re-ranked.