{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:59:03Z","timestamp":1775854743170,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2321123"],"award-info":[{"award-number":["2321123"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation","award":["2340982"],"award-info":[{"award-number":["2340982"]}]},{"name":"National Science Foundation","award":["2505106"],"award-info":[{"award-number":["2505106"]}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0024207"],"award-info":[{"award-number":["DE-SC0024207"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759827","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:05:39Z","timestamp":1762963539000},"page":"1368-1380","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["HPC-R1: Characterizing R1-like Large Reasoning Models on HPC"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0027-6549","authenticated-orcid":false,"given":"Adam","family":"Weingram","sequence":"first","affiliation":[{"name":"University of California, Merced, Merced, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7700-2798","authenticated-orcid":false,"given":"Duo","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1522-7686","authenticated-orcid":false,"given":"Zhonghao","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8795-5262","authenticated-orcid":false,"given":"Hao","family":"Qi","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7581-8905","authenticated-orcid":false,"given":"Xiaoyi","family":"Lu","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"Towards AGI. 2024. Llama 3.2 Benchmark Insights and Revolutionizing Edge AI and Vision. https:\/\/medium.com\/towards-agi\/llama-3-2-benchmark-insights-and-revolutionizing-edge-ai-and-vision-88542fe3dc0d."},{"key":"e_1_3_3_3_3_2","unstructured":"AWS. 2023. AWS OFI NCCL Plugin. https:\/\/github.com\/aws\/aws-ofi-nccl."},{"key":"e_1_3_3_3_4_2","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et\u00a0al. 2023. Qwen Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16609 (2023)."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell Jackson Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon Carol Chen Catherine Olsson Christopher Olah Danny Hernandez Dawn Drain Deep Ganguli Dustin Li Eli Tran-Johnson Ethan Perez Jamie Kerr Jared Mueller Jeffrey Ladish Joshua Landau Kamal Ndousse Kamile Lukosuite Liane Lovitt Michael Sellitto Nelson Elhage Nicholas Schiefer Noemi Mercado Nova DasSarma Robert Lasenby Robin Larson Sam Ringer Scott Johnston Shauna Kravec Sheer\u00a0El Showk Stanislav Fort Tamera Lanham Timothy Telleen-Lawton Tom Conerly Tom Henighan Tristan Hume Samuel\u00a0R. Bowman Zac Hatfield-Dodds Ben Mann Dario Amodei Nicholas Joseph Sam McCandlish Tom Brown and Jared Kaplan. 2022. Constitutional AI: Harmlessness from AI Feedback. 10.48550\/arXiv.2212.08073 arxiv:https:\/\/arXiv.org\/abs\/2212.08073\u00a0[cs]","DOI":"10.48550\/arXiv.2212.08073"},{"key":"e_1_3_3_3_6_2","unstructured":"Peter Braam. 2019. The Lustre Storage Architecture. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1903.01955 (2019)."},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-32041-510"},{"key":"e_1_3_3_3_8_2","unstructured":"Yushi Chen Zhihan Wu Bill\u00a0Yuchen Lin and Xiang Ren. 2025. Plan-to-Design: Empowering Reasoning in Language Models via Plan-Guided Design. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.11074 (2025). https:\/\/arxiv.org\/abs\/2503.11074"},{"key":"e_1_3_3_3_9_2","unstructured":"Chenggang Zhao Shangyan Zhou Liyue Zhang Chengqi Deng Zhean Xu Yuxuan Liu Kuai Yu Jiashi Li and Liang Zhao. 2025. DeepEP: An Efficient Expert-Parallel Communication Library. DeepSeek."},{"key":"e_1_3_3_3_10_2","volume-title":"Advances in Neural Information Processing Systems","author":"Christiano Paul\u00a0F","year":"2017","unstructured":"Paul\u00a0F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. In Advances in Neural Information Processing Systems , Vol.\u00a030. Curran Associates, Inc."},{"key":"e_1_3_3_3_11_2","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.14168 (2021). https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","unstructured":"Liuyao Dai Hao Qi Weicong Chen and Xiaoyi Lu. 2024. High-Speed Data Communication With Advanced Networks in Large Language Model Training. IEEE Micro 44 2 (March 2024) 31\u201340. 10.1109\/MM.2024.3360081","DOI":"10.1109\/MM.2024.3360081"},{"key":"e_1_3_3_3_13_2","unstructured":"Daniele De\u00a0Sensi Salvatore Di\u00a0Girolamo Kim\u00a0H. McMahon Duncan Roweth and Torsten Hoefler. 2020. An In-Depth Analysis of the Slingshot Interconnect. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2008.08886 (2020). https:\/\/arxiv.org\/abs\/2008.08886"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi Xiaokang Zhang Xingkai Yu Yu Wu Z.\u00a0F. Wu Zhibin Gou Zhihong Shao Zhuoshu Li Ziyi Gao Aixin Liu Bing Xue Bingxuan Wang Bochao Wu Bei Feng Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Honghui Ding Huajian Xin Huazuo Gao Hui Qu Hui Li Jianzhong Guo Jiashi Li Jiawei Wang Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li J.\u00a0L. Cai Jiaqi Ni Jian Liang Jin Chen Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Liang Zhao Litong Wang Liyue Zhang Lei Xu Leyi Xia Mingchuan Zhang Minghua Zhang Minghui Tang Meng Li Miaojun Wang Mingming Li Ning Tian Panpan Huang Peng Zhang Qiancheng Wang Qinyu Chen Qiushi Du Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang R.\u00a0J. Chen R.\u00a0L. Jin Ruyi Chen Shanghao Lu Shangyan Zhou Shanhuang Chen Shengfeng Ye Shiyu Wang Shuiping Yu Shunfeng Zhou Shuting Pan S.\u00a0S. Li Shuang Zhou Shaoqing Wu Shengfeng Ye Tao Yun Tian Pei Tianyu Sun T. Wang Wangding Zeng Wanjia Zhao Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang W.\u00a0L. Xiao Wei An Xiaodong Liu Xiaohan Wang Xiaokang Chen Xiaotao Nie Xin Cheng Xin Liu Xin Xie Xingchao Liu Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin X.\u00a0Q. Li Xiangyue Jin Xiaojin Shen Xiaosha Chen Xiaowen Sun Xiaoxiang Wang Xinnan Song Xinyi Zhou Xianzu Wang Xinxia Shan Y.\u00a0K. Li Y.\u00a0Q. Wang Y.\u00a0X. Wei Yang Zhang Yanhong Xu Yao Li Yao Zhao Yaofeng Sun Yaohui Wang Yi Yu Yichao Zhang Yifan Shi Yiliang Xiong Ying He Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yuan Ou Yuduan Wang Yue Gong Yuheng Zou Yujia He Yunfan Xiong Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Y.\u00a0X. Zhu Yanhong Xu Yanping Huang Yaohui Li Yi Zheng Yuchen Zhu Yunxian Ma Ying Tang Yukun Zha Yuting Yan Z.\u00a0Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhenda Xie Zhengyan Zhang Zhewen Hao Zhicheng Ma Zhigang Yan Zhiyu Wu Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Zizheng Pan Zhen Huang Zhipeng Xu Zhongyu Zhang and Zhen Zhang. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. 10.48550\/arXiv.2501.12948 arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs]","DOI":"10.48550\/arXiv.2501.12948"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J.\u00a0L. Cai Jian Liang Jianzhong Guo Jiaqi Ni Jiashi Li Jiawei Wang Jin Chen Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li Junxiao Song Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Lei Xu Leyi Xia Liang Zhao Litong Wang Liyue Zhang Meng Li Miaojun Wang Mingchuan Zhang Minghua Zhang Minghui Tang Mingming Li Ning Tian Panpan Huang Peiyi Wang Peng Zhang Qiancheng Wang Qihao Zhu Qinyu Chen Qiushi Du R.\u00a0J. Chen R.\u00a0L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S.\u00a0S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Shuting Pan T. Wang Tao Yun Tian Pei Tianyu Sun W.\u00a0L. Xiao Wangding Zeng Wanjia Zhao Wei An Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang X.\u00a0Q. Li Xiangyue Jin Xianzu Wang Xiao Bi Xiaodong Liu Xiaohan Wang Xiaojin Shen Xiaokang Chen Xiaokang Zhang Xiaosha Chen Xiaotao Nie Xiaowen Sun Xiaoxiang Wang Xin Cheng Xin Liu Xin Xie Xingchao Liu Xingkai Yu Xinnan Song Xinxia Shan Xinyi Zhou Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin Y.\u00a0K. Li Y.\u00a0Q. Wang Y.\u00a0X. Wei Y.\u00a0X. Zhu Yang Zhang Yanhong Xu Yanhong Xu Yanping Huang Yao Li Yao Zhao Yaofeng Sun Yaohui Li Yaohui Wang Yi Yu Yi Zheng Yichao Zhang Yifan Shi Yiliang Xiong Ying He Ying Tang Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yu Wu Yuan Ou Yuchen Zhu Yuduan Wang Yue Gong Yuheng Zou Yujia He Yukun Zha Yunfan Xiong Yunxian Ma Yuting Yan Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Z.\u00a0F. Wu Z.\u00a0Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhen Huang Zhen Zhang Zhenda Xie Zhengyan Zhang Zhewen Hao Zhibin Gou Zhicheng Ma Zhigang Yan Zhihong Shao Zhipeng Xu Zhiyu Wu Zhongyu Zhang Zhuoshu Li Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Ziyi Gao and Zizheng Pan. 2024. DeepSeek-V3 Technical Report. 10.48550\/arXiv.2412.19437 arxiv:https:\/\/arXiv.org\/abs\/2412.19437\u00a0[cs]","DOI":"10.48550\/arXiv.2412.19437"},{"key":"e_1_3_3_3_16_2","unstructured":"DeepSpeed. 2025. deepspeedai\/Megatron-DeepSpeed. https:\/\/github.com\/deepspeedai\/Megatron-DeepSpeed"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP61940.2024.10858546"},{"key":"e_1_3_3_3_18_2","unstructured":"Hugging Face. 2025. huggingface\/safetensors. https:\/\/github.com\/huggingface\/safetensors"},{"key":"e_1_3_3_3_19_2","unstructured":"James Fahey. 2024. Large Reasoning Models (LRMs): An Overview. Medium (2024). https:\/\/medium.com\/@fahey_james\/large-reasoning-models-lrms-an-overview-19837b72540f."},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807623"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"William Gropp Ewing Lusk Nathan Doss and Anthony Skjellum. 1996. A High-Performance Portable Implementation of the MPI Message Passing Interface Standard. Parallel Comput. 22 6 (1996) 789\u2013828. 10.1016\/0167-8191(96)00024-5","DOI":"10.1016\/0167-8191(96)00024-5"},{"key":"e_1_3_3_3_22_2","volume-title":"Unsloth","author":"Han Daniel","year":"2023","unstructured":"Daniel Han, Michael Han, and Unsloth team. 2023. Unsloth. http:\/\/github.com\/unslothai\/unsloth"},{"key":"e_1_3_3_3_23_2","unstructured":"Jingcheng Hu Yinmin Zhang Qi Han Daxin Jiang Xiangyu Zhang and Heung-Yeung Shum. 2025. Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model. arxiv:https:\/\/arXiv.org\/abs\/2503.24290\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2503.24290"},{"key":"e_1_3_3_3_24_2","unstructured":"Introducing OpenAI o1-Preview. 2024. https:\/\/openai.com\/index\/introducing-openai-o1-preview\/."},{"key":"e_1_3_3_3_25_2","unstructured":"Kathy Kincade. 2021. Berkeley Lab Deploys Next-Gen Supercomputer Perlmutter Bolstering U.S. Scientific Research. https:\/\/www.nersc.gov\/news-publications\/nersc-news\/nersc-center-news\/2021\/berkeley-lab-deploys-next-generation-supercomputer-perlmutter-bolstering-u-s-scientific-research\/. Accessed: 2025-04-11."},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"S. Kullback and R.\u00a0A. Leibler. 1951. On Information and Sufficiency. The Annals of Mathematical Statistics 22 1 (March 1951) 79\u201386. 10.1214\/aoms\/1177729694","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_3_28_2","unstructured":"Zhong-Zhi Li Duzhen Zhang Ming-Liang Zhang Jiaxin Zhang Zengyan Liu Yuxuan Yao Haotian Xu Junhao Zheng Pei-Jie Wang Xiuyi Chen et\u00a0al. 2025. From System 1 to System 2: A Survey of Reasoning Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.17419 (2025)."},{"key":"e_1_3_3_3_29_2","unstructured":"Zichen Liu Changyu Chen Wenjun Li Tianyu Pang Chao Du and Min Lin. 2025. There May Not be Aha Moment in R1-Zero-like Training \u2014 A Pilot Study. https:\/\/oatllm.notion.site\/oat-zero. Notion Blog."},{"key":"e_1_3_3_3_30_2","unstructured":"Michael Luo Sijun Tan Justin Wong Xiaoxiang Shi William\u00a0Y. Tang Manan Roongta Colin Cai Jeffrey Luo Li\u00a0Erran Li Raluca\u00a0Ada Popa and Ion Stoica. 2025. DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL. https:\/\/pretty-radio-b75.notion.site\/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2."},{"key":"e_1_3_3_3_31_2","unstructured":"Meta AI. 2024. Introducing Llama 3.2: Advancing Open Models for Edge and Vision AI. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/. Accessed: 2025-04-11."},{"key":"e_1_3_3_3_32_2","unstructured":"Microsoft. 2020. Pipeline Parallelism. https:\/\/www.deepspeed.ai\/tutorials\/pipeline\/."},{"key":"e_1_3_3_3_33_2","unstructured":"Microsoft. 2025. microsoft\/microxcaling. https:\/\/github.com\/microsoft\/microxcaling"},{"key":"e_1_3_3_3_34_2","first-page":"561","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael\u00a0I. Jordan, and Ion Stoica. 2018. Ray: A Distributed Framework for Emerging {AI} Applications. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 561\u2013577."},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Niklas Muennighoff Zitong Yang Weijia Shi Xiang\u00a0Lisa Li Li Fei-Fei Hannaneh Hajishirzi Luke Zettlemoyer Percy Liang Emmanuel Cand\u00e8s and Tatsunori Hashimoto. 2025. S1: Simple Test-Time Scaling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.19393 (2025).","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"e_1_3_3_3_36_2","unstructured":"NVIDIA. 2024. NVIDIA Nsight Systems. NVIDIA Corporation."},{"key":"e_1_3_3_3_37_2","unstructured":"NVIDIA. 2025. NVIDIA Tools Extension SDK (NVTX). NVIDIA Corporation."},{"key":"e_1_3_3_3_38_2","unstructured":"NVIDIA Corporation. 2018. Apex: PyTorch Extension for Mixed Precision and Distributed Training. https:\/\/github.com\/NVIDIA\/apex."},{"key":"e_1_3_3_3_39_2","unstructured":"NVIDIA Corporation. 2020. NVIDIA A100 Tensor Core GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/. Accessed: 2025-04-11."},{"key":"e_1_3_3_3_40_2","unstructured":"NVIDIA Corporation. 2022. NVIDIA Hopper Architecture In-Depth. https:\/\/www.nvidia.com\/en-us\/data-center\/h100\/."},{"key":"e_1_3_3_3_41_2","unstructured":"NVIDIA Corporation. 2023. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_3_3_42_2","unstructured":"Open R1. 2024. https:\/\/github.com\/huggingface\/open-r1."},{"key":"e_1_3_3_3_43_2","unstructured":"Open R1. 2025. OpenR1-Math-220k: A Large-Scale Dataset for Mathematical Reasoning. https:\/\/huggingface.co\/datasets\/open-r1\/OpenR1-Math-220k."},{"key":"e_1_3_3_3_44_2","volume-title":"o3 and o4-mini System Card","year":"2025","unstructured":"OpenAI. 2025. o3 and o4-mini System Card. 33 pages. https:\/\/cdn.openai.com\/pdf\/2221c875-02dc-4789-800b-e7758f3722c1\/o3-and-o4-mini-system-card.pdf"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul\u00a0F. Christiano Jan Leike and Ryan Lowe. 2022. Training Language Models to Follow Instructions with Human Feedback. Advances in Neural Information Processing Systems 35 (Dec. 2022) 27730\u201327744.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_3_3_46_2","unstructured":"Jiayi Pan Junjie Zhang Xingyao Wang Lifan Yuan Hao Peng and Alane Suhr. 2025. TinyZero. https:\/\/github.com\/Jiayi-Pan\/TinyZero. Accessed: 2025-01-24."},{"key":"e_1_3_3_3_47_2","unstructured":"Ajith Prakash. 2025. Latent Reasoning: The Next Evolution in AI for Scalable Adaptive and Efficient Problem Solving. https:\/\/ajithp.com\/2025\/02\/14\/latent-reasoning-the-next-evolution-in-ai-for-scalable-adaptive-and-efficient-problem-solving\/."},{"key":"e_1_3_3_3_48_2","unstructured":"PyTorch\/XLA Development Team. 2025. PyTorch\/XLA: PyTorch on XLA Devices. https:\/\/pytorch.org\/xla\/."},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI59126.2023.00022"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. 10.48550\/arXiv.1707.06347 arxiv:https:\/\/arXiv.org\/abs\/1707.06347\u00a0[cs]","DOI":"10.48550\/arXiv.1707.06347"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y.\u00a0K. Li Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. 10.48550\/arXiv.2402.03300 arxiv:https:\/\/arXiv.org\/abs\/2402.03300\u00a0[cs]","DOI":"10.48550\/arXiv.2402.03300"},{"key":"e_1_3_3_3_53_2","unstructured":"Guangming Sheng Chi Zhang Zilingfeng Ye Xibin Wu Wang Zhang Ru Zhang Yanghua Peng Haibin Lin and Chuan Wu. 2024. Hybridflow: A Flexible and Efficient RLHF Framework. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.19256 (2024)."},{"key":"e_1_3_3_3_54_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2021. Scaling Language Model Training to a Trillion Parameters Using Megatron. https:\/\/developer.nvidia.com\/blog\/scaling-language-model-training-to-a-trillion-parameters-using-megatron."},{"key":"e_1_3_3_3_55_2","unstructured":"Open\u00a0Thoughts Team. 2025. Open Thoughts."},{"key":"e_1_3_3_3_56_2","unstructured":"Zihan Wang* Kangrui Wang* Qineng Wang* Pingyue Zhang* Linjie Li* Zhengyuan Yang Kefan Yu Minh\u00a0Nhat Nguyen Monica Lam Yiping Lu Kyunghyun Cho Jiajun Wu Li Fei-Fei Lijuan Wang Yejin Choi and Manling Li. 2025. Training Agents by Reinforcing Reasoning. https:\/\/github.com\/ZihanWang314\/ragen"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Advances in neural information processing systems 35 (2022) 24824\u201324837.","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","unstructured":"Adam Weingram Yuke Li Hao Qi Darren Ng Liuyao Dai and Xiaoyi Lu. 2023. xCCL: A Survey of Industry-Led Collective Communication Libraries for Deep Learning. Journal of Computer Science and Technology 38 1 (Feb. 2023) 166\u2013195. 10.1007\/s11390-023-2894-6","DOI":"10.1007\/s11390-023-2894-6"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"crossref","unstructured":"Liang Wen Yunke Cai Fenrui Xiao Xin He Qi An Zhenyu Duan Yimin Du Junchen Liu Lifu Tang Xiaowei Lv Haosheng Zou Yongchao Deng Shousheng Jia and Xiangzheng Zhang. 2025. Light-R1: Curriculum SFT DPO and RL for Long COT from Scratch and Beyond. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10460 (2025).","DOI":"10.18653\/v1\/2025.acl-industry.24"},{"key":"e_1_3_3_3_60_2","unstructured":"Ling Yang Zhaochen Yu Bin Cui and Mengdi Wang. 2025. ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.06772 (2025)."},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1007\/10968987_3"},{"key":"e_1_3_3_3_62_2","unstructured":"Weizhe Yuan Jane Yu Song Jiang Karthik Padthe Yang Li Dong Wang Ilia Kulikov Kyunghyun Cho Yuandong Tian Jason Weston and Xian Li. 2025. NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions. arxiv:https:\/\/arXiv.org\/abs\/2502.13124\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.13124"},{"key":"e_1_3_3_3_63_2","unstructured":"Weihao Zeng Yuzhen Huang Qian Liu Wei Liu Keqing He Zejun Ma and Junxian He. 2025. Simplerl-zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.18892 (2025)."},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","unstructured":"Yanli Zhao Andrew Gu Rohan Varma Liang Luo Chien-Chin Huang Min Xu Less Wright Hamid Shojanazeri Myle Ott Sam Shleifer Alban Desmaison Can Balioglu Pritam Damania Bernard Nguyen Geeta Chauhan Yuchen Hao Ajit Mathews and Shen Li. 2023. PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel. 10.48550\/arXiv.2304.11277 arxiv:https:\/\/arXiv.org\/abs\/2304.11277\u00a0[cs]","DOI":"10.48550\/arXiv.2304.11277"},{"key":"e_1_3_3_3_65_2","unstructured":"Yanyan Zhou Hongyin Liu Bo Li et\u00a0al. 2025. Reflective Translation with Reasoning Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10351 (2025). https:\/\/arxiv.org\/abs\/2503.10351"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3712285.3759827","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759827","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:38:44Z","timestamp":1773254324000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759827"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":64,"alternative-id":["10.1145\/3712285.3759827","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759827","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}