# Cosmos-LLaVA: Chatting with the Visual Cosmos-LLaVA: G"orselle Sohbet Etmek

arXiv: https://arxiv.org/abs/2412.02760 · HTML: https://mlsanity.com/paper/2412.02760/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)

## Built on by (most cited first, 1 of 1)

- [OCRTurk: A Comprehensive OCR Benchmark for Turkish](https://mlsanity.com/paper/2602.03693/) (2026)

## Abstract (arXiv)

In this study, a Turkish visual instruction model was developed and various model architectures and dataset combinations were analysed to improve the performance of this model. The Cosmos-LLaVA model, which is built by combining different large language models and image coders, is designed to overcome the deficiencies in the Turkish language. In the experiments, the effects of fine-tuning with various datasets on the model performance are analysed in detail. The results show that model architecture and dataset selection have a significant impact on performance. Bu ccalicsmada bir T"urkcce g"orsel talimat modeli gelicstirilerek bu modelin performansini artirmaya y"onelik ccecsitli model mimarileri ve veri k"umesi kombinasyonlari derinlemesine incelenmicstir. Farkli b"uy"uk dil modelleri ve g"or"unt"u kodlayicilarinin bir araya getirilmesiyle olucsturulan Cosmos-LLaVA modeli, T"urkcce dilindeki eksiklikleri gidermeye y"onelik olarak tasarlanmicstir. Yapilan deneylerde, ccecsitli veri k"umeleri ile yapilan ince ayarlarin model performansini nasil etkilediugi detayli olarak ele alinmicstir. Sonucclar, model mimarisi ve veri k"umesi secciminin performans "uzerinde "onemli bir etkiye sahip olduugunu g"ostermektedir.