Mahmud ElHuseyni 🇵🇸's picture

Mahmud ElHuseyni 🇵🇸

MElHuseyni

·

AI & ML interests

Computer Vision NLP Machine Learning

Recent Activity

liked a dataset 2 days ago

iletisim/dezenformasyon-bultenleri

liked a model 3 days ago

Omartificial-Intelligence-Space/basira-omni-30b-v0.1

reacted to cihatyldz's post with ❤️ 5 days ago

Şifahane, a dual-inference medical classification demo, is now live on Spaces. It features side-by-side Turkish BERT and Qwen2.5 architectures for real-time evaluation of the "Classifier vs. LLM" trade-offs, all within a single space. The system utilizes a fine-tuned Turkish BERT for high-speed, cost-effective inference and the Qwen2.5-7B model for flexible multi-task reasoning, with support for department classification, condition analysis, urgency assessment, and rationale generation across 12 medical departments. 🧠 BERT model: https://lnkd.in/dCUUASqq 📊 Dataset: https://lnkd.in/dGK9y24w 🤗 Demo: https://lnkd.in/dtWjCCPF

View all activity

Organizations

upvoted a collection 7 days ago

Granite Embedding

Embedding models (bi‑encoders and rerankers) for RAG, semantic search, and retrieval tasks. • 9 items • Updated 8 days ago • 42

upvoted a collection 10 days ago

Qwen3Guard

7 items • Updated Dec 31, 2025 • 67

upvoted 2 collections 11 days ago

AgenticQwen

3 items • Updated Apr 1 • 3

gpt-oss

OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats. • 16 items • Updated 16 days ago • 49

upvoted a collection 12 days ago

🤔 Facial Expressions Recognition

Embrace the future of Facial Expressions Recognition with the latest AI-powered technologies! 🚀 • 4 items • Updated Jun 11, 2024 • 10

upvoted a paper 12 days ago

RAG-Anything: All-in-One RAG Framework

Paper • 2510.12323 • Published Oct 14, 2025 • 81

upvoted a collection 14 days ago

DeepSeek-V4

4 items • Updated 14 days ago • 618

upvoted a collection 16 days ago

Qwen3.6

4 items • Updated 16 days ago • 319

upvoted 2 papers 16 days ago

RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models

Paper • 2604.19321 • Published 17 days ago • 7

OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Paper • 2604.18486 • Published 18 days ago • 90

upvoted an article 17 days ago

Article

QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard

17 days ago

•

11

upvoted a collection 17 days ago

DenseOn & LateOn

A collection of open state-of-the-art single and multi-vector models • 7 items • Updated 17 days ago • 9

upvoted an article 17 days ago

Article

DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models

17 days ago

•

37

upvoted a paper 18 days ago

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips

Paper • 2502.07408 • Published 22 days ago • 59

upvoted a paper 20 days ago

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

Paper • 2604.14164 • Published Mar 23 • 35

upvoted an article 21 days ago

Article

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

22 days ago

•

69

upvoted 2 papers 22 days ago

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

Paper • 2604.10866 • Published 25 days ago • 65

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published about 1 month ago • 187

upvoted a collection 23 days ago

BERT-as-a-Judge

10 items • Updated 22 days ago • 4

upvoted an article 27 days ago

Article

Multimodal Embedding & Reranker Models with Sentence Transformers

29 days ago

•

57