| SVD-softmax: Fast softmax approximation on large vocabulary neural networks K Shim, M Lee, I Choi, Y Boo, W Sung Advances in neural information processing systems 30, 2017 | 56 | 2017 |
| Understanding the role of self attention for efficient speech recognition K Shim, J Choi, W Sung International Conference on Learning Representations, 2022 | 55 | 2022 |
| Toward intelligent millimeter and terahertz communication for 6G: Computer vision-aided beamforming Y Ahn, J Kim, S Kim, K Shim, J Kim, S Kim, B Shim IEEE Wireless Communications 30 (5), 179-186, 2022 | 54 | 2022 |
| Semantic feature extraction for generalized zero-shot learning J Kim, K Shim, B Shim Proceedings of the AAAI conference on artificial intelligence 36 (1), 1166-1173, 2022 | 44 | 2022 |
| Vision transformer-based feature extraction for generalized zero-shot learning J Kim, K Shim, J Kim, B Shim ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 16 | 2023 |
| Layer-wise pruning of transformer attention heads for efficient language modeling K Shim, I Choi, W Sung, J Choi 2021 18th International SoC Design Conference (ISOCC), 357-358, 2021 | 13 | 2021 |
| Role of Sensing and Computer Vision in 6G Wireless Communications S Kim, J Moon, J Kim, Y Ahn, D Kim, S Kim, K Shim, B Shim arXiv preprint arXiv:2405.03945, 2024 | 11 | 2024 |
| Similarity and content-based phonetic self attention for speech recognition K Shim, W Sung INTERSPEECH 2022, 2022 | 8 | 2022 |
| Pseudo-label-free weakly supervised semantic segmentation using image masking S Kim, LT Nguyen, K Shim, J Kim, B Shim IEEE Access 10, 19401-19411, 2022 | 8 | 2022 |
| Terngemm: General matrix multiply library with ternary weights for fast dnn inference S Choi, K Shim, J Choi, W Sung, B Shim 2021 IEEE Workshop on Signal Processing Systems (SiPS), 111-116, 2021 | 6 | 2021 |
| Task-agnostic open-set prototype for few-shot open-set recognition B Kim, JT Lee, K Shim, S Chang 2023 IEEE International Conference on Image Processing (ICIP), 31-35, 2023 | 5 | 2023 |
| Depth-relative self attention for monocular depth estimation K Shim, J Kim, G Lee, B Shim International Joint Conference on Artificial Intelligence (IJCAI-23), 2023 | 5 | 2023 |
| A comparison of transformer, convolutional, and recurrent neural networks on phoneme recognition K Shim, W Sung arXiv preprint arXiv:2210.00367, 2022 | 4 | 2022 |
| Semantic-preserving augmentation for robust image-text retrieval S Kim, K Shim, LT Nguyen, B Shim ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 3 | 2023 |
| Exploring Attention Map Reuse for Efficient Transformer Neural Networks K Shim, J Choi, W Sung arXiv preprint arXiv:2301.12444, 2023 | 3 | 2023 |
| Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer K Shim, J Lee, S Chang, K Hwang INTERSPEECH 2023, 2023 | 2 | 2023 |
| Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data S Yang, B Kim, K Shim, S Chang INTERSPEECH 2023, 2023 | 2 | 2023 |
| Spatial Cross-Attention for Transformer-Based Image Captioning KA Ngo, K Shim, B Shim ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 2 | 2023 |
| Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models D Kim, G Lee, K Shim, B Shim arXiv preprint arXiv:2411.00029, 2024 | 1 | 2024 |
| Infinipot: Infinite context processing on memory-constrained llms M Kim, K Shim, J Choi, S Chang arXiv preprint arXiv:2410.01518, 2024 | 1 | 2024 |
Byonghyo ShimProfessor, Department of Electrical and Computer Engineering, Seoul National UniversityE-mail megerősítve itt: snu.ac.kr