Blog(3)
Research in Automatic Speech Recognition (ASR) continues to show that larger models yield better results. But while state-of-the-art networks continue to grow with billions of parameters, the difficulty of deploying these models on device also increases.
Images and videos have been at the forefront of digital media consumption for a long time. All aspects of video and image capture, transmission, and display have seen leaps of innovation in recent times.
Convolutional neural networks (CNNs) are widely used today in various vision tasks such as classification, detection and segmentation. To make full use of GPU in CNN model processing and to use batch normalization, images of various resolutions are usually resized to the same resolution in the pipeline with mostly used bilinear interpolation.
Research Areas(0)
Publications(35)
Dynamic Low-rank Estimation for Transformer-based Language Models
AuthorTing Hua,Retiree,Shangqian Gao,Yen-Chang Hsu,Yilin Shen,Hongxia Jin
PublishedConference on Empirical Methods in Natural Language Processing (EMNLP)
Date2023-12-08
LEARNING TO JOINTLY SHARE AND PRUNE WEIGHTS FOR GROUNDING BASED VISION AND LANGUAGE MODELS
AuthorShangqian Gao,Burak Uzkent,Yilin Shen,Hongxia Jin
PublishedInternational Conference on Learning Representation (ICLR)
Date2023-05-01
Dynamic Code Compression for JavaScript Engine
AuthorHyukwoo Park, Seonghyun Kim, Boram Bae (Samsung Research)
PublishedSoftware: Practice and Experience
Date2023-02-04
News(5)
Since the scale of the state-of-the-art AI models has become deeper, model compression also has been attracting more attention as a method to let models be deployed on edge devices without accessing cloud servers.
Automatic Speech Recognition (ASR) systems on smart devices have traditionally relied on server based models. This involves sending audio data to the server and receiving text hypothesis once the server model completes decoding.
Others(1)
What we do Working at Samsung Research is more than just a job. Find out how our researchers enjoy their work and are passionate about making a positive impact in the world. PlayVideo thumbnail - leehojung AI: Language Understanding Lee Ho-jung PlayVideo thumbnail - leejaewon AI: Speech Recognition Lee Jae-won PlayVideo thumbnail - kimkyungsoo AI: Visual Perception Kim Kyung-su PlayVideo thumbnail - hammyungjoo AI: On-Device AI Software Ham Myung-joo PlayVi...