Categories
Companies
Research
Sign in
Join
Loading the SOTA2 catalog…
WizWand is now SOTA2 Research
SOTA2
Research
Papers
Benchmarks
Datasets
Tasks
Multimodal AI research – Page 4 · SOTA2 Research
Back to Research
Research domain
Multimodal
Search tasks
Search
14 benchmarks · 59 papers
Multimodal Model Evaluation
14 benchmarks · 20 papers
Vision-Language Evaluation
14 benchmarks · 15 papers
Text-to-Audio
14 benchmarks · 9 papers
Compositional Evaluation
14 benchmarks · 6 papers
Audio-Visual Deepfake Detection
14 benchmarks · 40 papers
Multi-modal Evaluation
14 benchmarks · 10 papers
Multimodal Reward Modeling
13 benchmarks · 1 papers
ROI-level Visual Question Answering
13 benchmarks · 4 papers
Multimodal Code Generation
13 benchmarks · 12 papers
Cross-Reenactment
13 benchmarks · 6 papers
Multimodal Machine Unlearning
13 benchmarks · 6 papers
Visual Text Generation
13 benchmarks · 14 papers
Downstream Task Evaluation
13 benchmarks · 11 papers
Multiple-choice Visual Question Answering
13 benchmarks · 7 papers
Audio-Visual Captioning
13 benchmarks · 7 papers
Image-to-Audio Retrieval
12 benchmarks · 30 papers
Multimodal Math Reasoning
12 benchmarks · 26 papers
Multi-image Reasoning
12 benchmarks · 9 papers
VQA
12 benchmarks · 10 papers
Dense Captioning
12 benchmarks · 18 papers
Image Question Answering
12 benchmarks · 9 papers
Human-Object Interaction Generation
12 benchmarks · 16 papers
Hateful Meme Detection
12 benchmarks · 2 papers
Multimodal Segmentation
12 benchmarks · 13 papers
Few-shot Learning
12 benchmarks · 2 papers
Grounding & counting
12 benchmarks · 43 papers
Visual Entailment
11 benchmarks · 5 papers
Visual Instruction Tuning
11 benchmarks · 5 papers
Real-world Understanding
11 benchmarks · 15 papers
Multiple-choice Video Question Answering
11 benchmarks · 8 papers
Text-to-motion retrieval
11 benchmarks · 12 papers
Multimodal Named Entity Recognition
Page 4 of 83
Previous
Next