Ben Koska

I am passionate about new technologies in the area of Artificial Intelligence, with a focus on synthetic data. I have had the opportunity to work in multiple start-ups leading the design and development of several products.

Career

Publications

Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model

2nd International Conference On Foundation And Large Language Models

AuthorNov 2024

We present a novel 4.5B parameter small language model that can handle multiple input and output modalities, including text, images, videos, and audio. Despite its small size, the model achieves near state-of-the-art performance on a variety of tasks, demonstrating the potential of multi-modal models to tackle complex real-world problems. Our approach leverages recent advancements in language modeling and multi-task learning to create a versatile and high-performing model that can even be deployed for edge inference. Experimental results show the model's strong performance across multiple benchmarks, paving the way for further progress in multi-modal artificial intelligence.

Artificial IntelligenceMulti-ModalSmall Language Model

Simulated Realities are all you need: Synthetic Data for Enhanced Depth, Localization, and Object Detection in egocentric views

Under review

AuthorNov 2024

Augmented reality (AR) applications require precise spatial understanding to facilitate accurate mapping, object detection, and scene comprehension. However, real-world data for training such tasks is often difficult to obtain - and especially difficult to label - at scale and lacks the diversity needed for robust model performance. This paper introduces a synthetic data framework to advance AR capabilities, leveraging simulated environments with realistic lighting, textures, and complex scene interactions.

Synthetic DataDepth EstimationLocalizationObject Detection

Volunteering

Patents

Education

Licenses & Certifications

Speaking

Languages

English

Native proficiency

German

Native proficiency