merve's picture

merve PRO

merve

·

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

AI & ML interests

I love this website VLMs, vision & co

Recent Activity

posted an update about 10 hours ago

large AI labs have dropped so many open models last week 🔥 don't miss out on them → Apple released on-device vision LMs https://huggingface.co/collections/apple/fastvlm-68ac97b9cd5cacefdd04872e & https://huggingface.co/collections/apple/mobileclip2-68ac947dcb035c54bcd20c47 → OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) https://huggingface.co/collections/OpenGVLab/internvl35-68ac87bd52ebe953485927fb → MSFT released a killer small TTS model (OS) https://huggingface.co/microsoft/VibeVoice-1.5B find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486

liked a model about 10 hours ago

openbmb/MiniCPM-V-4_5

updated a collection about 10 hours ago

August 29 Releases

View all activity

Organizations

upvoted 2 articles 5 days ago

Article

Introducing Marvis TTS: Real-Time Streaming Speech Synthesis

By

and 1 other •

5 days ago

• 9

Article

NVIDIA Releases 6 Million Multi-Lingual Reasoning Dataset

By

and 4 others •

12 days ago

• 15

upvoted 5 papers 6 days ago

Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decode

Paper • 2508.04107 • Published 27 days ago • 4

CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation

Paper • 2411.10086 • Published Nov 15, 2024 • 2

OpenCUA: Open Foundations for Computer-Use Agents

Paper • 2508.09123 • Published 20 days ago • 30

FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping

Paper • 2506.07080 • Published Jun 8 • 6

Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

Paper • 2508.07785 • Published 22 days ago • 25

upvoted a collection 6 days ago

InternVL3.5

This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated 3 days ago • 79

upvoted a collection 18 days ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated 11 days ago • 264

upvoted 2 articles 18 days ago

Article

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

By

and 4 others •

21 days ago

• 68

Article

How To Build a News Agent with GPT-OSS, Hugging Face Inference & Gradio

By

•

18 days ago

• 21

upvoted a collection 21 days ago

MM Grounding DINO

8 items • Updated Aug 1 • 5

upvoted a collection 22 days ago

MM Grounding DINO

See: https://github.com/huggingface/transformers/pull/37925 • 8 items • Updated Jun 26 • 4

upvoted a collection about 1 month ago

Step3

2 items • Updated Jul 31 • 19

upvoted 2 articles about 1 month ago

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

By

and 4 others •

Jul 29

• 164

Article

Build an AI Shopping Assistant with Gradio MCP Servers

By

•

Jul 31

• 52

upvoted a changelog about 1 month ago

Changelog

Introducing HF Jobs: Run scalable compute jobs on Hugging Face

Jul 30

• 151

upvoted 3 articles about 1 month ago

Article

Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨

By

and 2 others •

Jul 25

• 80

Article

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

By

•

Jul 16

• 136

Article

TimeScope: How Long Can Your Video Large Multimodal Model Go?

By

and 3 others •

Jul 23

• 39