5 27 72

Umitcan Sahin PRO

ucsahin

AI & ML interests

Visual Language Models, Large Language Models, Vision Transformers

Recent Activity

reacted to singhsidhukuldeep's post with 🔥 2 days ago

Exciting News in AI: JinaAI Releases JINA-CLIP-v2! The team at Jina AI has just released a groundbreaking multilingual multimodal embedding model that's pushing the boundaries of text-image understanding. Here's why this is a big deal: 🚀 Technical Highlights: - Dual encoder architecture combining a 561M parameter Jina XLM-RoBERTa text encoder and a 304M parameter EVA02-L14 vision encoder - Supports 89 languages with 8,192 token context length - Processes images up to 512×512 pixels with 14×14 patch size - Implements FlashAttention2 for text and xFormers for vision processing - Uses Matryoshka Representation Learning for efficient vector storage ⚡️ Under The Hood: - Multi-stage training process with progressive resolution scaling (224→384→512) - Contrastive learning using InfoNCE loss in both directions - Trained on massive multilingual dataset including 400M English and 400M multilingual image-caption pairs - Incorporates specialized datasets for document understanding, scientific graphs, and infographics - Uses hard negative mining with 7 negatives per positive sample 📊 Performance: - Outperforms previous models on visual document retrieval (52.65% nDCG@5) - Achieves 89.73% image-to-text and 79.09% text-to-image retrieval on CLIP benchmark - Strong multilingual performance across 30 languages - Maintains performance even with 75% dimension reduction (256D vs 1024D) 🎯 Key Innovation: The model solves the long-standing challenge of unifying text-only and multi-modal retrieval systems while adding robust multilingual support. Perfect for building cross-lingual visual search systems! Kudos to the research team at Jina AI for this impressive advancement in multimodal AI!

upvoted a collection 17 days ago

DataGemma Release

new activity 25 days ago

ucsahin/TR-VLM-DPO-Dataset:[bot] Conversion to Parquet

View all activity

Organizations

None yet

ucsahin's activity

liked a model 29 days ago

AIDC-AI/Marco-o1

Text Generation • Updated Nov 23 • 14.4k • 672

liked 2 datasets about 1 month ago

microsoft/orca-agentinstruct-1M-v1

Viewer • Updated Nov 1 • 1.05M • 12.9k • 404

mlabonne/orca-agentinstruct-1M-v1-cleaned

Viewer • Updated Nov 18 • 1.05M • 1.44k • 52

liked 2 models about 1 month ago

google/siglip-so400m-patch16-256-i18n

Zero-Shot Image Classification • Updated Nov 18 • 2.56k • 27

NexaAIDev/OmniVLM-968M

Updated 10 days ago • 3.79k • 485

liked 2 models about 2 months ago

gokaygokay/Flux-Seamless-Texture-LoRA

Text-to-Image • Updated Oct 30 • 394 • • 22

gokaygokay/Flux-Double-Exposure-LoRA

Text-to-Image • Updated Oct 29 • 198 • • 16

liked a model 2 months ago

Metin/Gemma-2-9b-it-TR-DPO-V1

Text Generation • Updated Oct 22 • 2.97k • 9

liked 2 models 3 months ago

Qwen/Qwen2-VL-7B-Instruct

Image-Text-to-Text • Updated 20 days ago • 2.42M • • 981

stepfun-ai/GOT-OCR2_0

Image-Text-to-Text • Updated Sep 18 • 985k • 1.31k

liked a model 4 months ago

ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1

Text Generation • Updated 23 days ago • 6.86k • 42

liked a Space 4 months ago

Running on Zero

990

😻

FLUX Prompt Generator

liked a model 4 months ago

atasoglu/Turkish-LLaVA-v0.1-Q4_K_M-GGUF

Image-Text-to-Text • Updated Aug 23 • 128 • 4

liked 3 Spaces 4 months ago

Running

📚

Chat With CosmosLLaMa

Running on Zero

139

⚡

Pony Realism / Cyber Realistic Pony / Stallion Dreams

Runtime error

😻

Blending

liked a Space 5 months ago

Running

💻

Vision Papers

All paper summaries read by Merve

liked 2 models 5 months ago

google/siglip-base-patch16-256-multilingual

Zero-Shot Image Classification • Updated Sep 26 • 51k • 37

ytu-ce-cosmos/turkish-gpt2-large

Text Generation • Updated May 7 • 4.78k • 35

liked a dataset 5 months ago

lmms-lab/LLaVA-OneVision-Data

Viewer • Updated Oct 22 • 3.72M • 11.7k • 149