4 206 195

Mahmud ElHuseyni 🇵🇸

MElHuseyni

AI & ML interests

Computer Vision NLP Machine Learning

Recent Activity

upvoted a collection about 3 hours ago

SigLIP2

commented on a paper about 8 hours ago

Mask-to-Height: A YOLOv11-Based Architecture for Joint Building Instance Segmentation and Height Classification from Satellite Imagery

new activity 2 days ago

huggingface/InferenceSupport:MElHuseyni/mxbai-edge-colbert-v0-17mv3-tr

View all activity

Organizations

upvoted a collection about 3 hours ago

SigLIP2

Collection

36 items • Updated Jul 10 • 92

commented a paper about 8 hours ago

Mask-to-Height: A YOLOv11-Based Architecture for Joint Building Instance Segmentation and Height Classification from Satellite Imagery

Paper • 2510.27224 • Published 3 days ago •

New activity in huggingface/InferenceSupport 2 days ago

MElHuseyni/mxbai-edge-colbert-v0-17mv3-tr

#5888 opened 2 days ago by

MElHuseyni

liked a dataset 5 days ago

unicamp-dl/mmarco

Updated Mar 6, 2024 • 1.79k • 84

upvoted 2 papers 5 days ago

Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution

Paper • 2509.24726 • Published Sep 29 • 19

Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets

Paper • 2204.05235 • Published Apr 11, 2022 • 1

liked a model 5 days ago

nvidia/Qwen2.5-VL-7B-Surg-CholecT50

Image-Text-to-Text • 8B • Updated 5 days ago • 29 • 7

liked a dataset 6 days ago

nvidia/Nemotron-VLM-Dataset-v2

Viewer • Updated 4 days ago • 4.58M • 1.7k • 41

upvoted an article 6 days ago

Article

Granite 4.0 Nano: Just how small can you go?

and 1 other •

6 days ago

• 96

upvoted a collection 6 days ago

Granite 4.0 Nano Language Models

Collection

9 items • Updated 3 days ago • 78

upvoted a paper 6 days ago

Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report

Paper • 2510.14880 • Published 18 days ago • 14

liked a model 6 days ago

LiquidAI/LFM2-ColBERT-350M

liked a dataset 6 days ago

ling99/OCRBench_v2

Viewer • Updated Feb 24 • 10k • 764 • 9

liked a dataset 7 days ago

coral-nlp/german-commons

Viewer • Updated 14 days ago • 21.8M • 2.79k • 23

upvoted a collection 7 days ago

Clara-Medical

Collection

NVIDIA Clara Open Models for medical imaging AI: segment, generate, and reason across CT, MRI, and X-ray. Built on MONAI by NVIDIA. • 7 items • Updated 7 days ago • 3

reacted to DmitryRyumin's post with 🔥 7 days ago

Post

4733

🚀🤖🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🤖🚀
📄 Title: Variance-based Pruning for Accelerating and Compressing Trained Networks 🔝

📝 Description: The one-shot pruning method efficiently compresses networks, reducing computation and memory usage while retaining almost full performance and requiring minimal fine-tuning.

👥 Authors: Uranik Berisha, Jens Mehnert, and Alexandru Paul Condurache

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Variance-Based Pruning for Accelerating and Compressing Trained Networks (2507.12988)

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #VarianceBasedPruning #NetworkCompression #ModelAcceleration #EfficientDeepLearning #VisionTransformers #AI #ICCV2025 #ResearchHighlight