ucsahin (Umitcan Sahin)

upvoted 2 papers 20 days ago

LLaVA-OneVision: Easy Visual Task Transfer

Paper • 2408.03326 • Published 27 days ago • 56

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

Paper • 2408.02718 • Published 28 days ago • 60

upvoted a paper 21 days ago

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Paper • 2408.05211 • Published 24 days ago • 46

upvoted 2 papers 29 days ago

SAM 2: Segment Anything in Images and Videos

Paper • 2408.00714 • Published Aug 1 • 100

Gemma 2: Improving Open Language Models at a Practical Size

Paper • 2408.00118 • Published Jul 31 • 72

upvoted a collection about 1 month ago

Vision Language Leaderboards

Collection

This collection has all the vision language leaderboards. • 7 items • Updated 9 days ago • 9

upvoted 2 articles about 1 month ago

Article

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

Jul 31

• 57

Article

The Rise of Agentic Data Generation

By

•

Jul 15

• 74

upvoted a paper about 1 month ago

EVLM: An Efficient Vision-Language Model for Visual Understanding

Paper • 2407.14177 • Published Jul 19 • 42

upvoted a paper about 2 months ago

Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model

Paper • 2407.07053 • Published Jul 9 • 41

upvoted a collection about 2 months ago

🪐 SmolLM

Collection

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated 16 days ago • 160

upvoted 2 articles about 2 months ago

Article

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Jul 18

• 41

Article

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 59

upvoted 4 papers about 2 months ago

upvoted an article 2 months ago

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Jun 24

• 162

upvoted a paper 2 months ago

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Paper • 2406.09406 • Published Jun 13 • 12

upvoted an article 3 months ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 298

upvoted a paper 3 months ago

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Paper • 2405.20204 • Published May 30 • 29

upvoted an article 3 months ago

Article

seemore: Implement a Vision Language Model from Scratch

By

•

Jun 23

• 55

Umitcan Sahin PRO

AI & ML interests

Organizations

ucsahin's activity

LLaVA-OneVision: Easy Visual Task Transfer

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

VITA: Towards Open-Source Interactive Omni Multimodal LLM

SAM 2: Segment Anything in Images and Videos

Gemma 2: Improving Open Language Models at a Practical Size

Vision Language Leaderboards

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

The Rise of Agentic Data Generation

EVLM: An Efficient Vision-Language Model for Visual Understanding

Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model

🪐 SmolLM

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Docmatix - a huge dataset for Document Visual Question Answering

Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing

AgentInstruct: Toward Generative Teaching with Agentic Flows

Multi-Object Hallucination in Vision-Language Models

ColPali: Efficient Document Retrieval with Vision Language Models

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Uncensor any LLM with abliteration

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

seemore: Implement a Vision Language Model from Scratch