Audio-visual video embedding quality across retrieval, classification, clustering, pair classification, zero-shot classification, and video-centric...
AI & ML interests
Massive Text Embeddings Benchmark
Recent Activity
View all activity
Papers
View all PapersMAEB is a comprehensive audio benchmark with 30 tasks spanning both audio-only and audio-text cross-modal evaluation. Tasks span 7 task types: retr...
The HUME benchmark is designed to evaluate the performance of text embedding models and humans on a comparable set of tasks. This captures areas wh...
-
HUME: Measuring the Human-Model Performance Gap in Text Embedding Task
Paper β’ 2510.10062 β’ Published β’ 10 -
mteb/HUMEEmotionClassification
Viewer β’ Updated β’ 16k β’ 52 -
mteb/HUMEToxicConversationsClassification
Viewer β’ Updated β’ 8.05k β’ 113 -
mteb/HUMETweetSentimentExtractionClassification
Viewer β’ Updated β’ 27.5k β’ 43
A collection of items telated the the MMTEB release
MIEB(Multilingual) is a comprehensive image embeddings benchmark, spanning 10 task types, covering 130 tasks and a total of 39 languages.
In ad...
This is a collection of MTEB papers (not exhaustive).
-
MAEB: Massive Audio Embedding Benchmark
Paper β’ 2602.16008 β’ Published β’ 25 -
HUME: Measuring the Human-Model Performance Gap in Text Embedding Task
Paper β’ 2510.10062 β’ Published β’ 10 -
MMTEB: Massive Multilingual Text Embedding Benchmark
Paper β’ 2502.13595 β’ Published β’ 50 -
MIEB: Massive Image Embedding Benchmark
Paper β’ 2504.10471 β’ Published β’ 21
Audio-visual video embedding quality across retrieval, classification, clustering, pair classification, zero-shot classification, and video-centric...
A collection of items telated the the MMTEB release
MAEB is a comprehensive audio benchmark with 30 tasks spanning both audio-only and audio-text cross-modal evaluation. Tasks span 7 task types: retr...
MIEB(Multilingual) is a comprehensive image embeddings benchmark, spanning 10 task types, covering 130 tasks and a total of 39 languages.
In ad...
The HUME benchmark is designed to evaluate the performance of text embedding models and humans on a comparable set of tasks. This captures areas wh...
-
HUME: Measuring the Human-Model Performance Gap in Text Embedding Task
Paper β’ 2510.10062 β’ Published β’ 10 -
mteb/HUMEEmotionClassification
Viewer β’ Updated β’ 16k β’ 52 -
mteb/HUMEToxicConversationsClassification
Viewer β’ Updated β’ 8.05k β’ 113 -
mteb/HUMETweetSentimentExtractionClassification
Viewer β’ Updated β’ 27.5k β’ 43
This is a collection of MTEB papers (not exhaustive).
-
MAEB: Massive Audio Embedding Benchmark
Paper β’ 2602.16008 β’ Published β’ 25 -
HUME: Measuring the Human-Model Performance Gap in Text Embedding Task
Paper β’ 2510.10062 β’ Published β’ 10 -
MMTEB: Massive Multilingual Text Embedding Benchmark
Paper β’ 2502.13595 β’ Published β’ 50 -
MIEB: Massive Image Embedding Benchmark
Paper β’ 2504.10471 β’ Published β’ 21