Mahmud ElHuseyni 🇵🇸

MElHuseyni's activity

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

upvoted a collection about 17 hours ago

ModernBERT-TR

Collection

A 150M-parameter Turkish encoder family of base and downstream task models. • 20 items • Updated 1 day ago • 9

upvoted a paper 1 day ago

Simple Projection Variants Improve ColBERT Performance

Paper • 2510.12327 • Published Oct 14, 2025 • 9

upvoted 2 papers 14 days ago

Vision as Unified Multimodal Generation

Paper • 2607.06560 • Published 15 days ago • 46

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2606.15007 • Published Jun 12 • 19

upvoted a paper 17 days ago

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 76

upvoted a paper 22 days ago

Unlimited OCR Works

Paper • 2606.23050 • Published about 1 month ago • 58

upvoted a paper 27 days ago

Small LLMs: Pruning vs. Training from Scratch

Paper • 2606.14150 • Published Jun 12 • 2

upvoted a paper about 1 month ago

Code as Agent Harness

Paper • 2605.18747 • Published May 18 • 225

upvoted a collection about 1 month ago

TranslateGemma

Collection

3 items • Updated about 9 hours ago • 245

upvoted 2 papers about 1 month ago

ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models

Paper • 2602.16609 • Published Feb 18 • 9

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

Paper • 2606.03264 • Published Jun 2 • 26

upvoted a paper about 2 months ago

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Paper • 2601.18491 • Published Jan 26 • 126

upvoted a collection about 2 months ago

AgentDoG

Collection

A Diagnostic Guardrail Framework for AI Agent Safety and Security • 12 items • Updated about 1 month ago • 112

upvoted a paper 2 months ago

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs

Paper • 2604.02045 • Published Apr 2 • 39

upvoted a collection 2 months ago

BidirLM-Embedding

Collection

BidirLM is a family of 5 frontier bidirectional encoders, including an omnimodal variant at 2.5B. • 6 items • Updated Apr 7 • 7

upvoted an article 2 months ago

view article

Article

Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever.

• 

MaziyarPanahi

•

Jul 16, 2025

• 156

upvoted 3 collections 2 months ago

MedGemma Release

Collection

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 9 items • Updated about 9 hours ago • 512

Health AI Developer Foundations (HAI-DEF)

Collection

Groups models released for use in health AI by Google. Read more about HAI-DEF at http://goo.gle/hai-def • 22 items • Updated about 9 hours ago • 229

Medical QA Datasets

Collection

A collection of medical question answering (QA) datasets • 23 items • Updated Feb 22, 2025 • 48

upvoted a collection 3 months ago

Granite Embedding

Collection

Embedding models (bi‑encoders and rerankers) for RAG, semantic search, and retrieval tasks. • 9 items • Updated 15 days ago • 47