Dogan Ozcan's picture

20 28

Dogan Ozcan

doganozcan

·

doganozcan

AI & ML interests

Computer Vision, VLMs

Recent Activity

liked a Space 6 days ago

lllyasviel/iclight-v2

upvoted an article 18 days ago

We now support VLMs in smolagents!

upvoted a collection 19 days ago

View all activity

Organizations

None yet

doganozcan's activity

upvoted an article 18 days ago

Article

We now support VLMs in smolagents!

19 days ago

• 77

upvoted a collection 19 days ago

ProLIP

Official ProLIP weights • 4 items • Updated Dec 9, 2024 • 6

upvoted a collection 21 days ago

DeepSeek-R1

8 items • Updated 22 days ago • 473

upvoted a collection 2 months ago

InternVL2.5

Better than InternVL 2.0 • 18 items • Updated Jan 10 • 83

upvoted 2 collections 3 months ago

AIMv2

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated Nov 22, 2024 • 71

LLM2CLIP

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 10 items • Updated Jan 8 • 55

upvoted an article 4 months ago

Article

Visually Multilingual: Introducing mcdse-2b

By

•

Oct 27, 2024

• 38

upvoted a paper 4 months ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7, 2024 • 169

upvoted a collection 4 months ago

CogVideo

10 items • Updated Nov 27, 2024 • 49

upvoted an article 4 months ago

Article

Inference for PROs

Sep 22, 2023

• 53

upvoted 2 papers 4 months ago

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published Sep 27, 2024 • 94

BRAVE: Broadening the visual encoding of vision-language models

Paper • 2404.07204 • Published Apr 10, 2024 • 19

upvoted an article 5 months ago

Article

Llama can now see and run on your device - welcome Llama 3.2

Sep 25, 2024

• 182

upvoted 4 collections 5 months ago

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 568

NIM Serverless Inference API

Models in this collection are available for inference via a serverless API powered by NVIDIA NIM. • 8 items • Updated 26 days ago • 23

Qwen2-VL

Vision-language model series based on Qwen2 • 16 items • Updated Dec 6, 2024 • 203

InternVL2.0

Expanding Performance Boundaries of Open-Source MLLM • 15 items • Updated Jan 10 • 91