Wanda++: Pruning Large Language Models via Regional Gradients.

Kai Zhen Yifan Yang Kai Zhen Bhavana Ganesh Aram Galstyan Goeric Huybrechts Markus Müller Jonas M. Kübler Rupak Vignesh Swaminathan Athanasios Mouchtaris Sravan Babu Bodapati Nathan Susanj Zheng Zhang Jack FitzGerald Abhishek Kumar Wanda++: Pruning Large Language Models via Regional Gradients. 4321-4333 2025 ACL (Findings) https://doi.org/10.18653/v1/2025.findings-acl.224 https://aclanthology.org/2025.findings-acl.224/ conf/acl/2025f db/conf/acl/acl2025f.html#YangZGGHMKSMBSZ25 Jiajun Zhou 0004 Yifan Yang Kai Zhen Ziyue Liu 0003 Yequan Zhao Ershad Banijamali Athanasios Mouchtaris Ngai Wong 0001 Zheng Zhang 0005 QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models. 5341-5359 2025 EMNLP https://doi.org/10.18653/v1/2025.emnlp-main.271 conf/emnlp/2025 db/conf/emnlp/emnlp2025.html#ZhouYZLZBMWZ25 streams/conf/emnlp Zhen Zhang Yifan Yang Kai Zhen Nathan Susanj Athanasios Mouchtaris Siegfried Kunzmann Zheng Zhang MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models. 18526-18543 2025 EMNLP https://doi.org/10.18653/v1/2025.emnlp-main.935 conf/emnlp/2025 db/conf/emnlp/emnlp2025.html#ZhangYZSMKZ25 streams/conf/emnlp Ryan Solgi Kai Zhen Rupak Vignesh Swaminathan Nathan Susanj Athanasios Mouchtaris Siegfried Kunzmann Zheng Zhang 0005 Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models. EMNLP (Findings) 2025 23674-23683 conf/emnlp/2025f https://doi.org/10.18653/v1/2025.findings-emnlp.1287 https://aclanthology.org/2025.findings-emnlp.1287/ db/conf/emnlp/emnlp2025f.html#SolgiZSSMKZ25 streams/conf/emnlp

Zhen Zhang Yifan Yang Kai Zhen Nathan Susanj Athanasios Mouchtaris Siegfried Kunzmann Zheng Zhang MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models. 2025 February abs/2502.11513 CoRR https://doi.org/10.48550/arXiv.2502.11513 db/journals/corr/corr2502.html#abs-2502-11513 streams/journals/corr

Jiajun Zhou 0004 Yifan Yang Kai Zhen Ziyue Liu 0003 Yequan Zhao Ershad Banijamali Athanasios Mouchtaris Ngai Wong 0001 Zheng Zhang 0005 QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models. 2025 February abs/2502.12346 CoRR https://doi.org/10.48550/arXiv.2502.12346 db/journals/corr/corr2502.html#abs-2502-12346 streams/journals/corr

Yifan Yang Kai Zhen Bhavana Ganesh Aram Galstyan Goeric Huybrechts Markus Müller Jonas M. Kübler Rupak Vignesh Swaminathan Athanasios Mouchtaris Sravan Babu Bodapati Nathan Susanj Zheng Zhang Jack FitzGerald Abhishek Kumar Wanda++: Pruning Large Language Models via Regional Gradients. 2025 March abs/2503.04992 CoRR https://doi.org/10.48550/arXiv.2503.04992 db/journals/corr/corr2503.html#abs-2503-04992 streams/journals/corr

Ryan Solgi Kai Zhen Rupak Vignesh Swaminathan Nathan Susanj Athanasios Mouchtaris Siegfried Kunzmann Zheng Zhang 0005 Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models. 2025 May abs/2505.14871 CoRR https://doi.org/10.48550/arXiv.2505.14871 db/journals/corr/corr2505.html#abs-2505-14871 streams/journals/corr

Kai Li Lingming Kong Xuebin Shao Cheng Zhang Ruixuan Xi Kai Zhen Yunpeng Qi Blind Spot Detection System Merging Scene Data Analysis. 612-614 2024 CIPAE https://doi.org/10.1109/CIPAE64326.2024.00117 conf/cipae/2024 db/conf/cipae/cipae2024.html#LiKSZXZQ24 Yifan Yang Kai Zhen Ershad Banijamali Athanasios Mouchtaris Zheng Zhang 0005 AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning. 977-995 2024 EMNLP https://doi.org/10.18653/v1/2024.emnlp-main.56 https://aclanthology.org/2024.emnlp-main.56 conf/emnlp/2024 db/conf/emnlp/emnlp2024.html#YangZBMZ24 Rupak Vignesh Swaminathan Grant P. Strimel Ariya Rastrow Sri Harish Mallidi Kai Zhen Hieu Duy Nguyen Nathan Susanj Athanasios Mouchtaris Max-Margin Transducer Loss: Improving Sequence-Discriminative Training Using a Large-Margin Learning Strategy. 12226-12230 2024 ICASSP https://doi.org/10.1109/ICASSP48485.2024.10446322 conf/icassp/2024 db/conf/icassp/icassp2024.html#SwaminathanSRMZ24 Yueming Zhu Qing Xu 0002 Kai Zhen Runlin Zhang Shunbo Wang Quantitative Analysis of Eye-Tracking Data Based on Information-Theoretic Tools for Measuring Driver Drowsiness. 1-6 2024 ICME https://doi.org/10.1109/ICME57554.2024.10687976 conf/icmcs/2024 db/conf/icmcs/icme2024.html#Zhu0ZZW24

Yunxiang Jiang Qing Xu Kai Zhen Yu Chen Quantitative Evaluation of driver's situation awareness in virtual driving through Eye tracking analysis. 2024 abs/2404.14817 CoRR https://doi.org/10.48550/arXiv.2404.14817 db/journals/corr/corr2404.html#abs-2404-14817

Yifan Yang Kai Zhen Ershad Banijamali Athanasios Mouchtaris Zheng Zhang 0005 AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning. 2024 abs/2406.18060 CoRR https://doi.org/10.48550/arXiv.2406.18060 db/journals/corr/corr2406.html#abs-2406-18060 streams/journals/corr

Martin Radfar Paulina Lyskawa Brandon Trujillo Yi Xie Kai Zhen Jahn Heymann Denis Filimonov Grant P. Strimel Nathan Susanj Athanasios Mouchtaris Conmer: Streaming Conformer Without Self-attention for Interactive Voice Assistants. 2198-2202 2023 INTERSPEECH https://doi.org/10.21437/Interspeech.2023-2228 conf/interspeech/2023 db/conf/interspeech/interspeech2023.html#RadfarLTXZHFSSM23

Kai Zhen Jongmo Sung Mi Suk Lee Seungkwon Beack Minje Kim 0001 Scalable and Efficient Neural Speech Coding: A Hybrid Design. 12-25 2022 30 IEEE ACM Trans. Audio Speech Lang. Process. https://doi.org/10.1109/TASLP.2021.3129353 db/journals/taslp/taslp30.html#ZhenSLBK22

Kai Zhen Hieu Duy Nguyen Raviteja Chinta Nathan Susanj Athanasios Mouchtaris Tariq Afzal Ariya Rastrow Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition. 3033-3037 2022 INTERSPEECH https://doi.org/10.21437/Interspeech.2022-874 conf/interspeech/2022 db/conf/interspeech/interspeech2022.html#ZhenNCSMAR22 Kai Zhen Martin Radfar Hieu Duy Nguyen Grant P. Strimel Nathan Susanj Athanasios Mouchtaris Sub-8-Bit Quantization for On-Device Speech Recognition: A Regularization-Free Approach. 15-22 2022 SLT https://doi.org/10.1109/SLT54892.2023.10022821 conf/slt/2022 db/conf/slt/slt2022.html#ZhenRNSSM22

Kai Zhen Hieu Duy Nguyen Raviteja Chinta Nathan Susanj Athanasios Mouchtaris Tariq Afzal Ariya Rastrow Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition. 2022 abs/2206.15408 CoRR https://doi.org/10.48550/arXiv.2206.15408 db/journals/corr/corr2206.html#abs-2206-15408

Kai Zhen Martin Radfar Hieu Duy Nguyen Grant P. Strimel Nathan Susanj Athanasios Mouchtaris Sub-8-bit quantization for on-device speech recognition: a regularization-free approach. 2022 abs/2210.09188 CoRR https://doi.org/10.48550/arXiv.2210.09188 db/journals/corr/corr2210.html#abs-2210-09188

Haici Yang Kai Zhen Seungkwon Beack Minje Kim Source-Aware Neural Speech Coding for Noisy Speech Compression. 706-710 2021 ICASSP https://doi.org/10.1109/ICASSP39728.2021.9413678 conf/icassp/2021 db/conf/icassp/icassp2021.html#YangZBK21 Kai Zhen Hieu Duy Nguyen Feng-Ju Chang Athanasios Mouchtaris Ariya Rastrow Sparsification via Compressed Sensing for Automatic Speech Recognition. 6009-6013 2021 ICASSP https://doi.org/10.1109/ICASSP39728.2021.9413844 conf/icassp/2021 db/conf/icassp/icassp2021.html#ZhenNCMR21

Kai Zhen Mi Suk Lee Jongmo Sung Seungkwon Beack Minje Kim Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding. 2021 abs/2101.00054 CoRR https://arxiv.org/abs/2101.00054 db/journals/corr/corr2101.html#abs-2101-00054

Kai Zhen Hieu Duy Nguyen Feng-Ju Chang Athanasios Mouchtaris Ariya Rastrow Sparsification via Compressed Sensing for Automatic Speech Recognition. 2021 abs/2102.04932 CoRR https://arxiv.org/abs/2102.04932 db/journals/corr/corr2102.html#abs-2102-04932

Kai Zhen Jongmo Sung Mi Suk Lee Seungkwon Beack Minje Kim Scalable and Efficient Neural Speech Coding. 2021 abs/2103.14776 CoRR https://arxiv.org/abs/2103.14776 db/journals/corr/corr2103.html#abs-2103-14776

Kai Zhen Mi Suk Lee Jongmo Sung Seungkwon Beack Minje Kim 0001 Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding. 2159-2163 2020 27 IEEE Signal Process. Lett. https://doi.org/10.1109/LSP.2020.3039765 db/journals/spl/spl27.html#ZhenLSBK20

Kai Zhen Mi Suk Lee Jongmo Sung Seungkwon Beack Minje Kim Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization. 361-365 2020 ICASSP https://doi.org/10.1109/ICASSP40776.2020.9054347 conf/icassp/2020 db/conf/icassp/icassp2020.html#ZhenLSBK20 Kai Zhen Mi Suk Lee Minje Kim A Dual-Staged Context Aggregation Method towards Efficient End-to-End Speech Enhancement. 366-370 2020 ICASSP https://doi.org/10.1109/ICASSP40776.2020.9054499 conf/icassp/2020 db/conf/icassp/icassp2020.html#ZhenLK20

Kai Zhen Mi Suk Lee Jongmo Sung Seungkwon Beack Minje Kim Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization. 2020 abs/2002.05604 CoRR https://arxiv.org/abs/2002.05604 db/journals/corr/corr2002.html#abs-2002-05604

Kai Zhen Jongmo Sung Mi Suk Lee Seungkwon Beack Minje Kim Cascaded Cross-Module Residual Learning Towards Lightweight End-to-End Speech Coding. 3396-3400 2019 INTERSPEECH https://doi.org/10.21437/Interspeech.2019-1816 conf/interspeech/2019 db/conf/interspeech/interspeech2019.html#ZhenSLBK19

Kai Zhen Jongmo Sung Mi Suk Lee Seungkwon Beack Minje Kim Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding. 2019 abs/1906.07769 CoRR http://arxiv.org/abs/1906.07769 db/journals/corr/corr1906.html#abs-1906-07769

Kai Zhen Mi Suk Lee Minje Kim Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network. 2019 abs/1908.06468 CoRR http://arxiv.org/abs/1908.06468 db/journals/corr/corr1908.html#abs-1908-06468

Kai Zhen Aswin Sivaraman Jongmo Sung Minje Kim On Psychoacoustically Weighted Cost Functions Towards Resource-Efficient Deep Neural Networks for Speech Denoising. 2018 abs/1801.09774 CoRR http://arxiv.org/abs/1801.09774 db/journals/corr/corr1801.html#abs-1801-09774

Kai Zhen Mridul Birla David J. Crandall Bingjing Zhang Judy Qiu Hybrid Supervised-unsupervised Image Topic Visualization with Convolutional Neural Network and LDA. 2017 abs/1703.05243 CoRR http://arxiv.org/abs/1703.05243 db/journals/corr/corr1703.html#ZhenBCZQ17

Liang Bao Qian Li Kai Zhen Wei Xiang Ping Chen A functional flavor of service composition. 2344-2348 2011 FSKD https://doi.org/10.1109/FSKD.2011.6020002 conf/fskd/2011 db/conf/fskd/fskd2011.html#BaoLZXC11 Tariq Afzal Seyed Ershad BanijamaliErshad Banijamali Liang Bao Seungkwon Beack Mridul Birla Sravan Babu Bodapati Feng-Ju Chang Ping Chen Yu Chen Raviteja Chinta David CrandallDavid J. Crandall Denis Filimonov Jack FitzGerald Aram Galstyan Bhavana Ganesh Jahn Heymann Goeric Huybrechts Yunxiang Jiang Minje Kim Minje Kim 0001 Lingming Kong Jonas M. Kübler Abhishek Kumar Siegfried Kunzmann Mi Suk Lee Kai Li Qian Li Ziyue Liu 0003 Paulina Lyskawa Sri Harish Reddy MallidiSri Harish Mallidi Athanasios Mouchtaris Markus Müller Hieu Duy Nguyen Yunpeng Qi Judy Qiu Martin Radfar Ariya Rastrow Xuebin Shao Aswin Sivaraman Ryan Solgi Grant P. Strimel Jongmo Sung Nathan Susanj Rupak Vignesh Swaminathan Brandon Trujillo Shunbo Wang Ngai Wong 0001 Ruixuan Xi Wei Xiang Yi Xie Qing Xu Qing Xu 0002 Haici Yang Yifan Yang Bingjing Zhang Cheng Zhang Runlin Zhang Zhen Zhang Zheng Zhang Zheng Zhang 0005 Yequan Zhao Jiajun Zhou 0004 Yueming Zhu