Mahmud ElHuseyni 🇵🇸

MElHuseyni's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 3 days ago

view article

Article

Tokenmaxxing BERT: 50x faster tokenization

• 

huggingface

•

3 days ago

• 44

upvoted a collection 3 days ago

UltraBERT

Collection

UltraBERT: Beyond the Limit of BERT Pre-Training. Pre-trained 150M/380M encoders and a text embedding model, English, 32K context. • 4 items • Updated 4 days ago • 28

upvoted a collection 11 days ago

⛵ Vela 2.0

Collection

Towards Open Foundation Routing Models • 5 items • Updated 10 days ago • 31

upvoted a paper 23 days ago

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

Paper • 2609.26550 • Published 26 days ago • 43

upvoted 2 articles 24 days ago

view article

Article

mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench

• 

hotchpotch

•

Aug 13

• 10

view article

Article

Introducing jev-reranker: Reranking and Relevance Filtering for RAG

• 

hotchpotch

•

29 days ago

• 10

upvoted a collection 25 days ago

Kev

Collection

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own • 6 items • Updated 16 days ago • 34

upvoted a collection about 1 month ago

WeMM-Embedding

Collection

4 items • Updated about 5 hours ago • 33

upvoted 2 papers about 1 month ago

Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training

Paper • 2608.29313 • Published Aug 29 • 3

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published Sep 1 • 517

upvoted a paper about 2 months ago

MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum

Paper • 2608.25768 • Published Aug 26 • 5

upvoted a collection about 2 months ago

MoganBERT

Collection

MoganBERT Turkish Pre-Trained Encoder Collection • 5 items • Updated 20 days ago • 7

upvoted an article about 2 months ago

view article

Article

LEMUR and Mean Centering for Late-Interaction Retrieval in txtai

• 

NeuML

•

Aug 13

• 9

upvoted a paper about 2 months ago

jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation

Paper • 2607.18152 • Published Jul 20 • 6

upvoted an article 2 months ago

view article

Article

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

• 
• 
• +1

tomaarsen, NohTow, raphaelsty

•

Aug 18

• 119

upvoted a paper 2 months ago

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published Aug 7 • 115

upvoted an article 2 months ago

view article

Article

FineBooks: are open OCR models good enough to unlock historical knowledge?

• 

finebooks

•

Aug 10

• 26

upvoted an article 3 months ago

view article

Article

mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models

• 

lightonai

•

Jul 30

• 40

upvoted a collection 3 months ago

ModernBERT-TR

Collection

A 150M-parameter Turkish encoder family of base and downstream task models. • 20 items • Updated Jul 20 • 14

upvoted a paper 3 months ago

Simple Projection Variants Improve ColBERT Performance

Paper • 2510.12327 • Published Oct 14, 2025 • 9