Dogan Ozcan

doganozcan

doganozcan

AI & ML interests

Computer Vision, VLMs

Recent Activity

upvoted a paper 5 days ago

SAM 3: Segment Anything with Concepts

upvoted a paper 16 days ago

LightRAG: Simple and Fast Retrieval-Augmented Generation

upvoted a collection 18 days ago

MetaCLIP2 Multilingual

View all activity

Organizations

None yet

liked a model 2 months ago

Qwen/Qwen3-VL-235B-A22B-Thinking

Image-Text-to-Text • 236B • Updated 4 days ago • 6k • • 331

liked a model 3 months ago

google/embeddinggemma-300m

liked 2 models 4 months ago

zai-org/GLM-4.1V-9B-Base

Image-Text-to-Text • 10B • Updated Oct 25 • 5.75k • 63

openai/gpt-oss-20b

Text Generation • 22B • Updated Aug 26 • 7.28M • • 4k

liked a Space 4 months ago

The Ultra-Scale Playbook

🌌

3.53k

The ultimate guide to training LLM on large GPU Clusters

liked a model 4 months ago

rednote-hilab/dots.ocr

Image-Text-to-Text • 3B • Updated about 1 month ago • 1M • 1.14k

liked 2 Spaces 4 months ago

Dots OCR

🏢

150

Extract and visualize layout from PDFs or images

vggt

🏆

429

VGGT (CVPR 2025)

liked a model 5 months ago

moonshotai/Kimi-K2-Instruct

Text Generation • 1T • Updated 23 days ago • 172k • • 2.27k

liked 2 models 6 months ago

ByteDance/Dolphin

Image-Text-to-Text • 0.4B • Updated Jul 16 • 3.98k • 507

deepseek-ai/DeepSeek-R1-0528

Text Generation • 685B • Updated May 29 • 358k • • 2.39k

liked a Space 7 months ago

Computer Agent

🖥

981

Interact with an AI agent to perform web tasks

liked a model 8 months ago

reducto/RolmOCR

Image-to-Text • 8B • Updated Apr 2 • 9.46k • 567

liked a model 9 months ago

google/gemma-3-27b-it

Image-Text-to-Text • 27B • Updated Mar 21 • 1.17M • • 1.72k

liked a Space 9 months ago

Multimodal OCR

🍍

379

nanonets ocr2 / olmocr / qwen2vl ocr / aya vision / rolmocr

liked 2 Spaces 11 months ago

MatchAnything

🏢

240

Find matching images based on input criteria

Stable Video Diffusion 1.1

📺

1.98k

Generate a video from a single image

liked a model 11 months ago

Qwen/QVQ-72B-Preview

Image-Text-to-Text • 73B • Updated Jan 12 • 406 • 609

liked 2 models 12 months ago

tencent/HunyuanVideo

Text-to-Video • Updated Mar 6 • 1.01k • • 2.08k

Qwen/Qwen2-VL-72B

Image-Text-to-Text • 73B • Updated Dec 6, 2024 • 202 • 80