We create new connections through advanced research and technology in vision, text, machine learning, UX and ethnography.
Our multidisciplinary approach to AI allows us to tackle challenges from different perspectives and gives greater meaning to our work.
On reinforcement learning and distribution matching for fine-tuning language models with no catastrophic forgetting
This blog article by Laurent Besacier covers the INTERSPEECH 2022 papers he was most interested in based on his current research interests in self-supervised speech models, scaling speech-to-text models, large language models and ASR architectures and end-to-end speech to text translation.
The NAVER LABS Europe Search and Recommendation team is presenting work on fairness in ranking and on sparse neural rankers such as SPLADE at this year’s SIGIR conference.
NAVER LABS Europe, together with colleagues from NAVER, LINE and WEBTOON will be in New Orleans. Visit the NAVER booth for job opportunities, internships, tech demos and more! 17 papers, workshop keynotes.