Blog(2)

• Pretrained Bidirectional Distillation for Machine Translation

  Initializing parameters by a pretrained masked language model (LM) [1] is a knowledge transfer method widely applied to natural language processing tasks. Following its success, pretrained neural machine translation (NMT) models have attracted more and more research interest [2,3,4,5].

• [INTERSPEECH 2022 Series #4] Cross-Modal Decision Regularization for Simultaneous Speech Translation

  In today’s world of virtual meetings, conferences, and multi-media, automatic speech translation offers a wide variety of applications. Traditional offline speech translation models used a cascade of speech recognition and text translation. In our prior works [1], we developed efficient techniques for end-to-end speech translation which outperforms traditional cascaded approaches.

Research Areas(0)

Publications(29)

• Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment

  AuthorYoung D. Kwon

  PublishedInternational Conference on Learning Representation (ICLR)

  Date2026-04-23

• Efficient Compositional Multi-tasking for On-device Large Language Models

  AuthorOndrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko

  PublishedThe 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)

  Date2025-11-04

• On-device System of Compositional Multi-tasking in Large Language Models

  AuthorOndrej Bohdal, Kyeng-Hun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay

  PublishedThe 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track (EMNLP Industry Track)

  Date2025-11-04

View More

News(16)

• [Blog] Real-Time Multilingual Video Subtitle Spotting on Resource-Constrained Devices

  Accurate real-time on-device video subtitles spotting is essential for many applications such as subtitle translation, text-to-speech conversion, video content comprehension

• [Blog] Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation

  Scene Text Recognition (STR) aims to automatically transcribe text in natural scenes, enabling applications in autonomous driving, augmented reality, language translation, and assistive technologies.

• How Machine Translation Team in Samsung R&D Institute Poland contributed to success of Galaxy AI

  In 2024, along with the new Galaxy S24 flagship mobile phone model, Samsung introduced Galaxy AI. This Artificial Intelligence powered technology package was aimed at helping users with every-day tasks, from translation of calls and transcriptions in chats and calls to editing pictures and searching with images.

View More

Others(1)

• Samsung AI Forum 2018

  Seoul, September 12 ~ 13 Samsung AI Forum is an academic event for the foremost minds of today’s world to come together and share their views on the current and future development of Artificial Intelligence technology. saif videoPlay Registration * Registration has been closed early due to the maximum capacity. Participants Anyone with an interest in AI technology including undergraduate and graduate students, university faculty members, researchers, and members of ...