no code implementations • 2 May 2024 • Seong-Joon Park, Hee-Youl Kwak, Sang-Hyo Kim, Yongjune Kim, Jong-Seon No
The mask matrices in these cross-attention blocks are determined by the code's parity-check matrix that delineates the relationship between magnitude and syndrome vectors.
no code implementations • 23 Feb 2024 • Jiwoong Im, Nayoung Kwon, Taewoo Park, Jiheon Woo, Jaeho Lee, Yongjune Kim
In our framework, the lightweight ViT model on the edge device acts as a semantic encoder, efficiently identifying and selecting the crucial image information required for the classification task.
no code implementations • 16 Oct 2023 • Junghyun Lee, Eunsang Lee, Young-Sik Kim, Yongwoo Lee, Joon-Woo Lee, Yongjune Kim, Jong-Seon No
Unlike the previous works approximating activation functions uniformly and conservatively, this paper presents a \emph{layerwise} degree optimization of activation functions to aggressively reduce the inference time while maintaining classification accuracy by taking into account the characteristics of each layer.
1 code implementation • NeurIPS 2023 • Hee-Youl Kwak, Dae-Young Yun, Yongjune Kim, Sang-Hyo Kim, Jong-Seon No
The proposed NMS decoder, optimized solely through novel training methods without additional modules, can be integrated into existing LDPC decoders without incurring extra hardware costs.
no code implementations • 16 Aug 2023 • Seong-Joon Park, Hee-Youl Kwak, Sang-Hyo Kim, Sunghwan Kim, Yongjune Kim, Jong-Seon No
In communication and storage systems, error correction codes (ECCs) are pivotal in ensuring data reliability.
no code implementations • 6 Oct 2022 • Seonhyeong Kim, Jiheon Woo, Daewon Seo, Yongjune Kim
Federated learning (FL) is a distributed method to train a global model over a set of local clients while keeping data localized.
no code implementations • Annual International Conference on the Theory and Applications of Cryptographic Techniques EUROCRYPT 2022: Advances in Cryptology – EUROCRYPT 2022 2022 • Yongwoo Lee, Joon-Woo Lee, Young-Sik Kim, Yongjune Kim, Jong-Seon No , HyungChul Kang
The Cheon-Kim-Kim-Song (CKKS) scheme (Asiacrypt’17) is one of the most promising homomorphic encryption (HE) schemes as it enables privacy-preserving computing over real (or complex) numbers.
no code implementations • 10 Sep 2019 • Yongjune Kim, Yuval Cassuto, Lav R. Varshney
Suppose that the base classifiers' outputs are noisy or communicated over noisy channels; these noisy outputs will degrade the final classification accuracy.
no code implementations • ICML 2017 • Charbel Sakr, Yongjune Kim, Naresh Shanbhag
We focus on numerical precision – a key parameter defining the complexity of neural networks.
no code implementations • 3 Jul 2016 • Charbel Sakr, Ameya Patil, Sai Zhang, Yongjune Kim, Naresh Shanbhag
Lower bounds on the data precision are derived in terms of the the desired classification accuracy and precision of the hyperparameters used in the classifier.