Blog(44)

• Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning

  Stable Diffusion [1] for Super Resolution (i.e. SD-SR), has been shown to produce steep improvements compared to previous SR approaches.

• 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.

• Multi-task Learning for Speech Emotion Recognition in Naturalistic Conditions

  Speech Emotion Recognition (SER) is a crucial task in human-computer interaction, enabling applications such as mental health monitoring, affective computing, and customer service automation.

View More

Research Areas(7)

• Artificial Intelligence

  Overview Artificial Intelligence In the future, AI technology will become much more prevalent and we will interact with smart devices on a daily basis. These devices will understand our needs via spoken commands, visual gestures, and other cues and be able to help and guide us appropriately. New AI technology in the home and in the workplace will enable us to carry out our routines more efficiently; however, we need to ensure that these technologies operate in a ...

• Data Intelligence

  Overview The importance and value of data is growing nowadays and recognized as driving forces of innovation and competitiveness in diverse industrial fields. As data generation is explosively gaining speed, the amount of data is also rapidly augmenting. However, it is not the large amount of data itself that leads to innovation, but the technology that enables using the data meaningfully. As Samsung Electronics operates within a wide range of business portfolios...

• Next Generation Communications

  Overview The communication technology provides the infrastructure needed to enable people and things (i.e., devices, places, etc.) to connect and interact with one another across physical and virtual spaces. It is the foundation of a smarter age in which AI and robots will become a common part of our daily lives. The communication technology will continue to evolve fast to connect people with machines and things through more and faster exchange of information. To...

View More

Publications(830)

• HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series

  AuthorSimon A. Lee, Cyrus Tanade, Hao Zhou, Juhyeon Lee, Megha Thukral, Minji Han, Rachel Choi, Md Sazzad Hissain Khan, Baiying Lu, Migyeong Gwak, Mehrab Bin Morshed, Viswam Nathan, Md Mahbubur Rahman, Li Zhu, Subramaniam Venkatraman, Sharanya Arcot Desai

  PublishedInternational Conference on Learning Representations (ICLR)

  Date2026-01-26

• Benchmarking Rotary Position Embeddings for Automatic Speech Recognition

  AuthorShucong Zhang, Titouan Parcollet, Rogier van Dalen,

  PublishedIEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)

  Date2025-12-06

• Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition

  AuthorTitouan Parcollet, Rogier van Dalen, Shucong Zhang

  PublishedIEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)

  Date2025-12-06

View More

News(473)

• [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] A Reinforcement Learning-Based Rate Control for Neural Video Compression

  Past years have witnessed the explosive growth of end-to-end neural video compression (NVC) approaches. Benefiting from the powerful nonlinear modeling capability of deep neural networks (DNN) and end-to-end optimization with extensive training data, the compression performance of the latest NVC solutions has surpassed that of traditional standards.

• [Blog] 6G AI/ML for Physical-layer: Part II - CSI compression with JSCM

  In modern wireless systems, the efficient acquisition of Channel State Information (CSI) has become increasingly critical, driven by the deployment of massive antenna arrays and the demand for higher spectral efficiency.

View More

Others(46)

• Samsung AI Forum 2021

  November 1-2, 2021 Live stream Watch Now Play Day 1 날짜November 1, 2021 주관Hosted by Samsung Advanced Institute of Technology videoReplay video Day 2 날짜November 2, 2021 주관Hosted by Samsung Research Schedule Day 2 November 2, 2021 Hosted by Samsung Research 09:00 - 09:20 Welcome & Introduction Sebastian Seung|Corporate President of Samsung Electronics >> Reference Papers >> 09:20 - 09:50 Keynote. How to Augment Supervised Learning with Reasoning >> Les...

• Samsung AI Forum 2021

  제5회 삼성 AI 포럼 2021.11.1 – 11.2 Live stream Watch Now Play Day 1 날짜2021.11.1(월) 주관삼성종합기술원 주관 주관다시보기 Day 2 날짜2021.11.2(화) 주관삼성리서치 주관 Schedule Day 2 11.2 (화) 삼성리서치 주관 09:00 - 09:20 Welcome & Introduction Sebastian Seung|Corporate President of Samsung Electronics >> Reference Papers >> 09:20 - 09:50 Keynote. How to Augment Supervised Learning with Reasoning >> Leslie Valiant|Professor, Harvard University 09:50 - 10:10 Panel Discussion [Moderator] Dani...

• Gallery

  SCPC 2021 SCPC 2021 September 4, 2021 SSTF 2021 SSTF 2021 August 17, 2021 SCPC 2020 SCPC 2020 November 7, 2020 SCPC 2020Play SCPC 2020 November 7, 2020 SAIF 2020 SAIF 2020 November 3, 2020 SAIF 2020 November 3, 2020 SOSCON 2020 SOSCON 2020 October 14, 2020 SOSCON 2020 October 14, 2020 SSTF 2020 SSTF 2020 August 18, 2020 SSTF 2020 August 18, 2020 SAIF 2019 SAIF 2019 November 4, 2019 SAIF 2019Play SAIF 2019 November 4, 2019 SSTF 2019 SSTF 2019 August 20, 2019 SSTF ...

View More