{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:55:43Z","timestamp":1761404143586,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","funder":[{"name":"Beijing Municipal Science and Technology Project","award":["No. Z231100010323002"],"award-info":[{"award-number":["No. Z231100010323002"]}]},{"name":"the National Natural Science Foundation of China","award":["Nos. 62306025, 92367204"],"award-info":[{"award-number":["Nos. 62306025, 92367204"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746262.3761973","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:52:23Z","timestamp":1761403943000},"page":"2-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SLMQuant: Benchmarking Small Language Model Quantization for Practical Deployment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5393-0000","authenticated-orcid":false,"given":"Jiacheng","family":"Wang","sequence":"first","affiliation":[{"name":"SKLCCSE School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6445-0571","authenticated-orcid":false,"given":"Yejun","family":"Zeng","sequence":"additional","affiliation":[{"name":"SKLCCSE School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1956-3367","authenticated-orcid":false,"given":"Jinyang","family":"Guo","sequence":"additional","affiliation":[{"name":"SKLCCSE School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1936-9396","authenticated-orcid":false,"given":"Yuqing","family":"Ma","sequence":"additional","affiliation":[{"name":"SKLCCSE School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4224-1318","authenticated-orcid":false,"given":"Aishan","family":"Liu","sequence":"additional","affiliation":[{"name":"SKLCCSE School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8425-4195","authenticated-orcid":false,"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[{"name":"SKLCCSE School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Guilherme Penedo, Lewis Tunstall, Andr\u00e9s Marafioti, Hynek Kydl\u00edcek, Agust\u00edn Piqueres Lajar\u00edn, Vaibhav Srivastav, et al.","author":"Allal Loubna Ben","year":"2025","unstructured":"Loubna Ben Allal, Anton Lozhkov, Elie Bakouch, Gabriel Mart\u00edn Bl\u00e1zquez, Guilherme Penedo, Lewis Tunstall, Andr\u00e9s Marafioti, Hynek Kydl\u00edcek, Agust\u00edn Piqueres Lajar\u00edn, Vaibhav Srivastav, et al. 2025. SmolLM2: When Smol Goes Big--Data-Centric Training of a Small Language Model. arXiv preprint arXiv:2502.02737 (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_2_1_3_1","volume-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457","author":"Clark Peter","year":"2018","unstructured":"Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Llmc: Benchmarking large language model quantization with a versatile compression toolkit. arXiv preprint arXiv:2405.06001","author":"Gong Ruihao","year":"2024","unstructured":"Ruihao Gong, Yang Yong, Shiqiao Gu, Yushi Huang, Chengtao Lv, Yunchen Zhang, Xianglong Liu, and Dacheng Tao. 2024. Llmc: Benchmarking large language model quantization with a versatile compression toolkit. arXiv preprint arXiv:2405.06001 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"JointPruning: Pruning networks along multiple dimensions for efficient point cloud processing","author":"Guo Jinyang","year":"2021","unstructured":"Jinyang Guo, Jiaheng Liu, and Dong Xu. 2021. JointPruning: Pruning networks along multiple dimensions for efficient point cloud processing. IEEE Transactions on Circuits and Systems for Video Technology (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197395"},{"key":"e_1_3_2_1_8_1","unstructured":"Jinyang Guo Wanli Ouyang and Dong Xu. 2020. Multi-Dimensional Pruning: A Unified Framework for Model Compression. In CVPR."},{"key":"e_1_3_2_1_9_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Guo Jinyang","year":"2024","unstructured":"Jinyang Guo, Jianyu Wu, Zining Wang, Jiaheng Liu, Ge Yang, Yifu Ding, Ruihao Gong, Haotong Qin, and Xianglong Liu. 2024. Compressing large language models by joint sparsification and quantization. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_10_1","volume-title":"Cbanet: Towards complexity and bitrate adaptive deep image compression using a single network","author":"Guo Jinyang","year":"2023","unstructured":"Jinyang Guo, Dong Xu, and Guo Lu. 2023. Cbanet: Towards complexity and bitrate adaptive deep image compression using a single network. IEEE Transactions on Image Processing (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Multidimensional Pruning and Its Extension: A Unified Framework for Model Compression","author":"Guo Jinyang","year":"2023","unstructured":"Jinyang Guo, Dong Xu, and Wanli Ouyang. 2023. Multidimensional Pruning and Its Extension: A Unified Framework for Model Compression. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Model compression using progressive channel pruning","author":"Guo Jinyang","year":"2020","unstructured":"Jinyang Guo, Weichen Zhang, Wanli Ouyang, and Dong Xu. 2020. Model compression using progressive channel pruning. IEEE Transactions on Circuits and Systems for Video Technology (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models. In Forty-first International Conference on Machine Learning.","author":"He Changyi","year":"2025","unstructured":"Changyi He, Yifu Ding, Jinyang Guo, Ruihao Gong, Haotong Qin, and Xianglong Liu. 2025. DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_14_1","volume-title":"Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)."},{"key":"e_1_3_2_1_15_1","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Keming Lu et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"J. Guo W. Ouyang and D. Xu. 2020. Channel pruning guided by classification loss and feature importance. In AAAI.","DOI":"10.1609\/aaai.v34i07.6720"},{"key":"e_1_3_2_1_17_1","unstructured":"Jiaheng Liu Jianhao Li Kaisiyuan Wang Hongcheng Guo Jian Yang Junran Peng Ke Xu Xianglong Liu and Jinyang Guo. 2024. LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling. In CVPR."},{"key":"e_1_3_2_1_18_1","volume-title":"Spinquant: Llm quantization with learned rotations. arXiv preprint arXiv:2405.16406","author":"Liu Zechun","year":"2024","unstructured":"Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, and Tijmen Blankevoort. 2024. Spinquant: Llm quantization with learned rotations. arXiv preprint arXiv:2405.16406 (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01509"},{"key":"e_1_3_2_1_20_1","volume-title":"Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)."},{"key":"e_1_3_2_1_21_1","volume-title":"Omniquant: Omnidirectionally calibrated quantization for large language models. arXiv preprint arXiv:2308.13137","author":"Shao Wenqi","year":"2023","unstructured":"Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, and Ping Luo. 2023. Omniquant: Omnidirectionally calibrated quantization for large language models. arXiv preprint arXiv:2308.13137 (2023)."},{"key":"e_1_3_2_1_22_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_23_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"ACM Multimedia","author":"Guo Jinyang","year":"2024","unstructured":"ZiningWang, Jinyang Guo, Ruihao Gong, Yang Yong, Aishan Liu, Yushi Huang, Jiaheng Liu, and Xianglong Liu. [n.d.]. PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models. In ACM Multimedia 2024."},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 38087--38099","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. Smoothquant: Accurate and efficient post-training quantization for large language models. In International conference on machine learning. PMLR, 38087--38099."},{"key":"e_1_3_2_1_26_1","volume-title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment. NeurIPS","author":"Yang Ge","year":"2024","unstructured":"Ge Yang, Changyi He, Jinyang Guo, Jianyu Wu, Yifu Ding, Aishan Liu, Haotong Qin, Pengliang Ji, and Xianglong Liu. 2024. LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment. NeurIPS (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830","author":"Zellers Rowan","year":"2019","unstructured":"Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830 (2019)."}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 3rd International Workshop on Rich Media With Generative AI"],"original-title":[],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:52:29Z","timestamp":1761403949000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746262.3761973"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":27,"alternative-id":["10.1145\/3746262.3761973","10.1145\/3746262"],"URL":"https:\/\/doi.org\/10.1145\/3746262.3761973","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]},"assertion":[{"value":"2025-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}