Katerina Luchinina is a Staff Research Scientist at Google DeepMind, based in London. Her primary research focus lies in the domain of generative AI, particularly in computer vision and multimodal learning. She has made significant contributions to advanced text-to-image and text-to-video generation models, aiming to create systems that can understand and generate complex, high-fidelity visual content from textual descriptions. Katerina's work often involves developing novel architectures and training methodologies for large-scale generative models. She completed her PhD at the University of Cambridge, where her research also centered on machine learning and computer vision. She is known for her contributions to influential projects that push the boundaries of AI's creative capabilities.
Katerina Luchinina's work history includes a series of influential roles in various companies. Here is a detailed list of his professional journey:
Played a significant role in the research and development of pioneering text-to-video models at Google, including Imagen Video, Phenaki, and Lumiere, advancing the state-of-the-art in AI video generation with a focus on quality, coherence, and controllability.
Achieved a senior research position at one of the world's foremost artificial intelligence research labs, recognized for her expertise in generative models and computer vision.
Successfully completed her doctoral studies at a leading global university, specializing in machine learning, likely with a focus on deep learning methods for computer vision and generative tasks, which laid the foundation for her impactful industry research.
Contributed to research improving the quality, realism, and semantic understanding of text-to-image synthesis models, enabling more accurate and detailed visual representations from textual prompts.
Psychology Institute (Russian Academy of Science) - Year 2007
State Academic University Humanities - Year 2007
Московский Городской Психолого-Педагогический Университет (МГППУ) - Year 2006
Российский Государственный Социальный Университет (бывший Московский Государственный Социальный Университет) - Year 2002
Highperformr Signals uncover buying intent and give you clear insights to target the right people at the right time — helping your sales, marketing, and GTM teams close more deals, faster.
PlayMotionTech is an innovative technology company at the forefront of creating next-generation interactive entertainment experiences. We specialize in developing advanced motion capture hardware, real-time animation software, and AI-driven character behavior systems for the gaming, virtual reality (VR), and metaverse industries. Our mission is to empower creators with tools that blur the lines between physical and digital realities, enabling more immersive and engaging user experiences.
Get verified emails, phone numbers, and LinkedIn profile details
Discover contacts with similar roles, seniority, or companies
Uncover insights like skills, work history, social links, and more
Explore contacts in-depth — from verified emails and phone numbers to LinkedIn activity, job changes, and more — all in one powerful view.
Highperformr AI helps you surface the right people and enrich your CRM with live, accurate contact insights so your teams can connect faster and close smarter.
Thousands of contacts — including decision-makers, influencers, and ICP matches — are just a search away.
Thousands of companies, including, are just a search away.