Mohammed Mohammed Ali PRO

MohammedEltoum

AI & ML interests

None yet

Recent Activity

upvoted a paper 6 days ago

SAM 3: Segment Anything with Concepts

upvoted a paper 15 days ago

Depth Anything 3: Recovering the Visual Space from Any Views

upvoted an article about 1 month ago

LeRobot v0.4.0: Supercharging OSS Robot Learning

View all activity

Organizations

upvoted a paper 6 days ago

SAM 3: Segment Anything with Concepts

Paper • 2511.16719 • Published 9 days ago • 92

upvoted a paper 15 days ago

Depth Anything 3: Recovering the Visual Space from Any Views

Paper • 2511.10647 • Published 16 days ago • 88

upvoted an article about 1 month ago

Article

LeRobot v0.4.0: Supercharging OSS Robot Learning

Oct 24

•

upvoted a paper about 1 month ago

AnyUp: Universal Feature Upsampling

Paper • 2510.12764 • Published Oct 14 • 11

upvoted 3 papers 3 months ago

Visual Representation Alignment for Multimodal Large Language Models

Paper • 2509.07979 • Published Sep 9 • 83

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

Paper • 2509.01644 • Published Sep 1 • 33

DINOv3

Paper • 2508.10104 • Published Aug 13 • 284

upvoted an article 4 months ago

Article

Vision Language Model Alignment in TRL ⚡️

Aug 7

•

101

upvoted 2 papers 4 months ago

MolmoAct: Action Reasoning Models that can Reason in Space

Paper • 2508.07917 • Published Aug 11 • 44

Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

Paper • 2507.23404 • Published Jul 31 • 2

reacted to sergiopaniego's post with 👍 4 months ago

Post

4545

Just included example scripts for aligning models using GSPO (including VLM example) 🙆‍♂️🙆‍♂️

GSPO is the latest RL alignment algo by @Alibaba_Qwen and it's already supported in the latest TRL v0.20 release.

Super-easy-to-get-started example scripts below, GO run them!👩‍💻👩‍💻

🧑‍🎨 Script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo.py
🦄 VLM script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo_vlm.py
🧩 More TRL examples: https://huggingface.co/docs/trl/main/en/example_overview
🧙‍♂️ GSPO paper: Group Sequence Policy Optimization (2507.18071)

liked a Space 4 months ago

Appoint Ready - MedGemma Demo

📋

146

Simulated Pre-visit Intake Demo built using MedGemma

reacted to merve's post with ❤️ 5 months ago

Post

2669

Fine-tune Gemma3n on videos with audios inside with Colab A100 🔥
Just dropped the notebook where you can learn how to fine-tune Gemma3n on images+audio+text at the same time!

keep in mind, it's made for educational purposes 🫡 we do LoRA, audio resampling & video downsampling to be able to train <40GB VRAM

stretch modalities and unfreeze layers as you wish! 🙏🏻 merve/smol-vision