Area-Efficient and Variation-Tolerant In-Memory BNN Computing using 6T SRAM Array J Kim, J Koo, T Kim, Y Kim, H Kim, S Yoo, JJ Kim 2019 Symposium on VLSI Circuits, C118-C119, 2019 | 82 | 2019 |
Improved Synapse Device With MLC and Conductance Linearity Using Quantized Conduction for Neuromorphic Systems S Lim, C Sung, H Kim, T Kim, J Song, JJ Kim, H Hwang IEEE Electron Device Letters 39 (2), 312-315, 2018 | 67 | 2018 |
Effect of conductance linearity and multi-level cell characteristics of TaOx-based synapse device on pattern recognition accuracy of neuromorphic system C Sung, S Lim, H Kim, T Kim, K Moon, J Song, JJ Kim, H Hwang Nanotechnology 29 (11), 115203, 2018 | 47 | 2018 |
Input voltage mapping optimized for resistive memory-based deep neural network hardware T Kim, H Kim, J Kim, JJ Kim IEEE Electron Device Letters 38 (9), 1228-1231, 2017 | 47 | 2017 |
OWQ: Lessons learned from activation outliers for weight quantization in large language models C Lee, J Jin, T Kim, H Kim, E Park arXiv preprint arXiv:2306.02272, 2023 | 37 | 2023 |
Deep neural network optimized to resistive memory with nonlinear current-voltage characteristics H Kim, T Kim, J Kim, JJ Kim ACM Journal on Emerging Technologies in Computing Systems (JETC) 14 (2), 1-17, 2018 | 28 | 2018 |
Bitblade: Energy-efficient variable bit-precision hardware accelerator for quantized neural networks S Ryu, H Kim, W Yi, E Kim, Y Kim, T Kim, JJ Kim IEEE Journal of Solid-State Circuits 57 (6), 1924-1935, 2022 | 26 | 2022 |
Efficient Synapse Memory Structure for Reconfigurable Digital Neuromorphic Hardware J Kim, J Koo, T Kim, JJ Kim Frontiers in Neuroscience 12, 2018 | 25 | 2018 |
Viterbi-based pruning for sparse matrix with fixed and high index compression ratio D Lee, D Ahn, T Kim, PI Chuang, JJ Kim International Conference on Learning Representations, 2018 | 22 | 2018 |
Double Viterbi: Weight encoding for high compression ratio and fast on-chip reconstruction for deep neural network D Ahn, D Lee, T Kim, JJ Kim International Conference on Learning Representations, 2018 | 13 | 2018 |
A 44.1 TOPS/W Precision-Scalable Accelerator for Quantized Neural Networks in 28nm CMOS S Ryu, H Kim, W Yi, J Koo, E Kim, Y Kim, T Kim, JJ Kim 2020 IEEE Custom Integrated Circuits Conference (CICC), 1-4, 2020 | 12 | 2020 |
Configurable BCAM/TCAM Based on 6T SRAM Bit Cell and Enhanced Match Line Clamping J Koo, E Kim, S Yoo, T Kim, S Ryu, JJ Kim 2019 IEEE Asian Solid-State Circuits Conference (A-SSCC), 223-226, 2019 | 11 | 2019 |
V-LSTM: An efficient LSTM accelerator using fixed nonzero-ratio viterbi-based pruning T Kim, D Ahn, D Lee, JJ Kim IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023 | 7 | 2023 |
Time-step interleaved weight reuse for LSTM neural network computing N Park, Y Kim, D Ahn, T Kim, JJ Kim Proceedings of the ACM/IEEE International Symposium on Low Power Electronics …, 2020 | 6 | 2020 |
OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models C Lee, J Jin, T Kim, H Kim, E Park Proceedings of the AAAI Conference on Artificial Intelligence 38 (12), 13355 …, 2024 | 3 | 2024 |
Squeezing Large-Scale Diffusion Models for Mobile J Choi, M Kim, D Ahn, T Kim, Y Kim, D Jo, H Jeon, JJ Kim, H Kim arXiv preprint arXiv:2307.01193, 2023 | 3 | 2023 |
SPRITE: Sparsity-Aware Neural Processing Unit with Constant Probability of Index-Matching S Ryu, Y Oh, T Kim, D Ahn, JJ Kim 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), 663-666, 2021 | 3 | 2021 |
Searching for Robust Binary Neural Networks via Bimodal Parameter Perturbation D Ahn, H Kim, T Kim, E Park, JJ Kim Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2023 | 1 | 2023 |
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference T Kim, J Lee, D Ahn, S Kim, J Choi, M Kim, H Kim arXiv preprint arXiv:2402.10076, 2024 | | 2024 |
SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks J Song, K Oh, T Kim, H Kim, Y Kim, JJ Kim arXiv preprint arXiv:2402.09025, 2024 | | 2024 |