Author: Ekrem Çetinkaya

126 POSTS0 COMMENTS
Ekrem Çetinkaya received his B.Sc. in 2018, and M.Sc. in 2019 from Ozyegin University, Istanbul, Türkiye. He wrote his M.Sc. thesis about image denoising using deep convolutional networks. He received his Ph.D. degree in 2023 from the University of Klagenfurt, Austria, with his dissertation titled "Video Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning." His research interests include deep learning, computer vision, video encoding, and multimedia networking.

The Hollywood at Home: DragNUWA is an AI Model That Can Achieve Controllable Video Generation

Generative AI has made a huge leap in the last two years thanks to the successful release of large-scale diffusion models. These models are...

The Trick to Make LLaMa Fit into Your Pocket: Meet OmniQuant, an AI Method that Bridges the Efficiency and Performance of LLMs

Large language models (LLMs), like the infamous ChatGPT, have achieved impressive performance on a variety of natural language processing tasks, such as machine translation,...

Magnifying the Invisible: This Artificial Intelligence AI Method Uses NeRFs for Visualizing Subtle Motions in 3D

We live in a world full of motion, from the subtle movements of our bodies to the large-scale movements of the earth. However, many...

Guess What I Saw Today? This AI Model Decodes Your Brain Signals to Reconstruct the Things You Saw

Brain 🧠. The most fascinating organ of the human body. Understanding how it works is the key to unlocking the secrets of life. How...

Is The Wait for Jurassic Park Over? This AI Model Uses Image-to-Image Translation to Bring Ancient Fossils to Life

Image-to-image translation (I2I) is an interesting field within computer vision and machine learning that holds the power to transform visual content from one domain...

Walk me Through Time: SceNeRFlow is an AI Method That Generates Time Consistent NeRFs

Neural Radiance Fields (NeRF) emerged as a transformative concept in the 3D domain recently. It reshaped how we handle the 3D object visualization and...

Make ChatGPT See Again: This AI Approach Explores Link-Context Learning to Enable Multimodal Learning

Language models have revolutionized the way we communicate with computers by their ability to generate coherent and contextually relevant text. Large Language Models (LLMs)...

Make ChatGPT a Better Software Developer: SoTaNa is an Open-Source AI Assistant for Software Development

How we do what we do has changed rapidly in recent years. We have started to use virtual assistants for most of the tasks...

The Enigma for ChatGPT: PUMA is an AI Approach That Proposes a Fast and Secure Way for LLM Inference

Large Language Models (LLMs) have started a revolution in the artificial intelligence domain. The release of ChatGPT has sparked the ignition for the era...

Watch and Learn Little Robot: This AI Approach Teaches Robots Generalizable Manipulation Using Human Video Demonstrations

Robots have always been at the center of attention in the tech landscape. They always found a place in sci-fi movies, kid shows, books,...

Not the Vader You Think of: 3D VADER is an AI Model That Diffuses 3D Models

Image generation has never been easier. With the rise of generative AI models, the process became really easy to start. It’s like you have...

Video Editing is a Challenge No More: INVE is an AI Method That Enables Interactive Neural Video Editing

Can you imagine the Internet without image editing? All those funny memes, fancy Instagram photos, mesmerizing sceneries, and more; would’ve been gone. That wouldn’t...