44 68 28

Solomatin Roman

Samoed

AI & ML interests

None yet

Recent Activity

updated a Space about 22 hours ago

mteb/README

updated a dataset 2 days ago

mteb/miracl_full

published a dataset 2 days ago

mteb/miracl_full

View all activity

Organizations

upvoted an article 6 days ago

Article

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

and 2 others •

6 days ago

• 52

upvoted an article 7 days ago

Article

Sentence Transformers is joining Hugging Face!

7 days ago

• 71

upvoted an article 9 days ago

Article

Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text

and 2 others •

9 days ago

• 33

upvoted a paper 14 days ago

Scaling Language-Centric Omnimodal Representation Learning

Paper • 2510.11693 • Published 16 days ago • 97

upvoted a paper 15 days ago

HUME: Measuring the Human-Model Performance Gap in Text Embedding Task

Paper • 2510.10062 • Published 18 days ago • 8

upvoted an article 24 days ago

Article

Vocabulary is the most important element of Sparse Retrieval

•

25 days ago

• 8

upvoted a paper 25 days ago

ModernVBERT: Towards Smaller Visual Document Retrievers

Paper • 2510.01149 • Published 28 days ago • 30

upvoted an article 26 days ago

Article

ModernVBERT: Towards Smaller Visual Document Retrievers

and 4 others •

26 days ago

• 41

upvoted a collection 26 days ago

ModernVBERT

Collection

Resources for ModernVBERT • 5 items • Updated 26 days ago • 11

upvoted an article 28 days ago

Article

Introducing RTEB: A New Standard for Retrieval Evaluation

28 days ago

• 117

upvoted a changelog about 1 month ago

Changelog

Repositories total file size is now displayed

Sep 18

• 170

upvoted a paper about 1 month ago

AutoIntent: AutoML for Text Classification

Paper • 2509.21138 • Published Sep 25 • 33

upvoted an article about 2 months ago

Article

mmBERT: ModernBERT goes Multilingual

Sep 9

• 117

upvoted a collection about 2 months ago

mmBERT: a modern multilingual encoder

Collection

mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance • 16 items • Updated Sep 9 • 46

upvoted 2 papers about 2 months ago

Dynaword: From One-shot to Continuously Developed Datasets

Paper • 2508.02271 • Published Aug 4 • 14

On the Theoretical Limitations of Embedding-Based Retrieval

Paper • 2508.21038 • Published Aug 28 • 19

upvoted an article 4 months ago

Article

Should We Still Pretrain Encoders with Masked Language Modeling?

and 3 others •

Jul 2

• 21

upvoted a paper 4 months ago

Maintaining MTEB: Towards Long Term Usability and Reproducibility of Embedding Benchmarks

Paper • 2506.21182 • Published Jun 26 • 2

upvoted 2 papers 5 months ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published May 27 • 139

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20 • 77

Solomatin Roman

AI & ML interests

Recent Activity

Organizations

Samoed's activity

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

Sentence Transformers is joining Hugging Face!

Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text

Vocabulary is the most important element of Sparse Retrieval

ModernVBERT: Towards Smaller Visual Document Retrievers

Introducing RTEB: A New Standard for Retrieval Evaluation

Repositories total file size is now displayed

mmBERT: ModernBERT goes Multilingual

Should We Still Pretrain Encoders with Masked Language Modeling?