Merve Noyan's picture

Merve Noyan PRO

merve

·

https://github.com/merveenoyan/smol-vision

AI & ML interests

VLMs, vision & co

Recent Activity

posted an update about 11 hours ago

introducing: VLM vibe eval 🪭 https://huggingface.co/spaces/visionLMsftw/VLMVibeEval vision LMs are saturated over benchmarks, so we built vibe eval 💬 > compare different models with refreshed in-the-wild examples in different categories 🤠 > submit your favorite model for eval no numbers -- just vibes!

published a Space about 11 hours ago

visionLMsftw/VLMVibeEval

updated a Space about 11 hours ago

visionLMsftw/VLMVibeEval

View all activity

Organizations

merve's activity

upvoted a paper 2 days ago

MMaDA: Multimodal Large Diffusion Language Models

Paper • 2505.15809 • Published 8 days ago • 83

upvoted a paper 3 days ago

Emerging Properties in Unified Multimodal Pretraining

Paper • 2505.14683 • Published 9 days ago • 124

upvoted an article 3 days ago

Article

Interactive Tools for machine learning, deep learning, and math

By

•

4 days ago

• 31

upvoted 2 changelogs 7 days ago

Changelog

Xet is now the default storage option for new users and organizations

7 days ago

• 46

Changelog

Static Spaces can now have a build step

7 days ago

• 68

upvoted an article 7 days ago

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

By

and 6 others •

9 days ago

• 115

upvoted a collection 7 days ago

SSR

Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning • 5 items • Updated 5 days ago • 1

upvoted a changelog 7 days ago

Changelog

AI-generated Abstract summaries on Hugging Face Papers

8 days ago

• 62

upvoted a collection 7 days ago

MedGemma Release

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 4 items • Updated 7 days ago • 136

upvoted a paper 10 days ago

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning

Paper • 2505.04601 • Published 22 days ago • 26

upvoted an article 10 days ago

Article

The Transformers Library: standardizing model definitions

By

and 3 others •

15 days ago

• 104

upvoted 4 collections 10 days ago

Cosmos Transfer1

Multimodal Conditional World Generation for World2World Transfer • 6 items • Updated 9 days ago • 17

Cosmos Tokenize1

A suite of image and video tokenizers • 9 items • Updated 9 days ago • 7

Cosmos Predict1

World Foundation Model for Future Prediction • 14 items • Updated 9 days ago • 7

Cosmos-Reason1

Multimodal world understanding through reasoning • 5 items • Updated 8 days ago • 24

upvoted a paper 10 days ago

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Paper • 2503.15558 • Published Mar 18 • 47

upvoted 2 articles 10 days ago

Article

Microsoft and Hugging Face expand collaboration

By

and 2 others •

11 days ago

• 20

Article

NVIDIA Cosmos Now Available On Hugging Face For Physical AI Reasoning

By

and 1 other •

10 days ago

• 24

upvoted a collection 14 days ago

Marigold Computer Vision

All things Marigold • 17 items • Updated 14 days ago • 17

upvoted an article 14 days ago

Article

Falcon-Edge: A series of powerful, universal, fine-tunable 1.58bit language models.

By

and 9 others •

15 days ago

• 32