| @inproceedings{vaswani2017attention, |
| title = {Attention Is All You Need}, |
| author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, { |
| }Lukasz and Polosukhin, Illia}, |
| booktitle = {Advances in Neural Information Processing Systems}, |
| year = {2017} |
| } |
| |
| @book{mckinney2017python, |
| title = {Python for Data Analysis}, |
| author = {McKinney, Wes}, |
| publisher = {O'Reilly Media}, |
| address = {Sebastopol, CA}, |
| year = {2017}, |
| edition = {2}, |
| isbn = {978-1491957660} |
| } |
| |
| @inproceedings{he2016resnet, |
| title = {Deep Residual Learning for Image Recognition}, |
| author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, |
| booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, |
| pages = {770--778}, |
| year = {2016}, |
| doi = {10.1109/CVPR.2016.90}, |
| url = {https://doi.org/10.1109/CVPR.2016.90} |
| } |
| |
| @article{silver2017mastering, |
| title = {Mastering the game of Go without human knowledge}, |
| author = {Silver, David and Schrittwieser, Julian and Simonyan, Karen and Antonoglou, Ioannis and Huang, Aja and others}, |
| journal = {Nature}, |
| volume = {550}, |
| number = {7676}, |
| pages = {354--359}, |
| year = {2017}, |
| month = {oct}, |
| doi = {10.1038/nature24270}, |
| url = {https://www.nature.com/articles/nature24270} |
| } |
| |
| @techreport{openai2023gpt4, |
| title = {GPT-4 Technical Report}, |
| author = {{OpenAI}}, |
| institution = {OpenAI}, |
| year = {2023}, |
| number = {arXiv:2303.08774}, |
| archiveprefix = {arXiv}, |
| eprint = {2303.08774}, |
| primaryclass = {cs.CL}, |
| url = {https://arxiv.org/abs/2303.08774} |
| } |
| |
| @phdthesis{doe2020thesis, |
| title = {Learning Efficient Representations for Large-Scale Visual Recognition}, |
| author = {Doe, Jane}, |
| school = {Massachusetts Institute of Technology}, |
| address = {Cambridge, MA}, |
| year = {2020}, |
| doi = {10.5555/mit-2020-xyz} |
| } |
| |
| @incollection{cover2006entropy, |
| title = {Entropy, Relative Entropy, and Mutual Information}, |
| author = {Cover, Thomas M. and Thomas, Joy A.}, |
| booktitle = {Elements of Information Theory}, |
| publisher = {Wiley}, |
| address = {Hoboken, NJ}, |
| edition = {2}, |
| year = {2006}, |
| pages = {13--55}, |
| isbn = {978-0471241959} |
| } |
| |
| @misc{zenodo2021dataset, |
| title = {ImageNet-21K Subset (Version 2.0)}, |
| author = {Smith, John and Lee, Alice and Kumar, Ravi}, |
| year = {2021}, |
| howpublished = {Dataset on Zenodo}, |
| doi = {10.5281/zenodo.1234567}, |
| url = {https://doi.org/10.5281/zenodo.1234567}, |
| note = {Accessed 2025-09-01} |
| } |
| |
| @misc{sklearn2024, |
| title = {scikit-learn: Machine Learning in Python (Version 1.4)}, |
| author = {Pedregosa, Fabian and Varoquaux, Ga{"e}l and Gramfort, Alexandre and others}, |
| year = {2024}, |
| howpublished = {Software}, |
| doi = {10.5281/zenodo.592264}, |
| url = {https://scikit-learn.org} |
| } |
| |
| @inproceedings{smith2024privacy, |
| title = {Privacy-Preserving Training with Low-Precision Secure Aggregation}, |
| author = {Smith, Emily and Zhang, Wei and Rossi, Marco and Patel, Neha}, |
| booktitle = {Proceedings of the 41st International Conference on Machine Learning}, |
| editor = {Smith, A. and Johnson, B.}, |
| series = {Proceedings of Machine Learning Research}, |
| volume = {235}, |
| pages = {12345--12367}, |
| address = {Vienna, Austria}, |
| publisher = {PMLR}, |
| month = {jul}, |
| year = {2024}, |
| url = {https://proceedings.mlr.press/v235/} |
| } |
| |
| @article{kingma2015adam, |
| title = {Adam: A Method for Stochastic Optimization}, |
| author = {Kingma, Diederik P. and Ba, Jimmy}, |
| journal = {International Conference on Learning Representations (ICLR)}, |
| year = {2015}, |
| archiveprefix = {arXiv}, |
| eprint = {1412.6980}, |
| primaryclass = {cs.LG}, |
| url = {https://arxiv.org/abs/1412.6980} |
| } |
| |
| @misc{raffel2020t5, |
| title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer}, |
| author = {Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and others}, |
| year = {2020}, |
| howpublished = {arXiv preprint}, |
| archiveprefix = {arXiv}, |
| eprint = {1910.10683}, |
| primaryclass = {cs.LG}, |
| doi = {10.48550/arXiv.1910.10683}, |
| url = {https://arxiv.org/abs/1910.10683} |
| } |
| |
| @misc{boizard2025crosstokenizerdistillationuniversallogit, |
| title={Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs}, |
| author={Nicolas Boizard and Kevin El Haddad and Céline Hudelot and Pierre Colombo}, |
| year={2025}, |
| eprint={2402.12030}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL}, |
| url={https://huggingface.co/papers/2402.12030}, |
| } |
| |
| @misc{agarwal2024onpolicydistillationlanguagemodels, |
| title={On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes}, |
| author={Rishabh Agarwal and Nino Vieillard and Yongchao Zhou and Piotr Stanczyk and Sabela Ramos and Matthieu Geist and Olivier Bachem}, |
| year={2024}, |
| eprint={2306.13649}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.LG}, |
| url={https://huggingface.co/papers/2306.13649}, |
| } |
| |
| @misc{gandhi2024streamsearchsoslearning, |
| title={Stream of Search (SoS): Learning to Search in Language}, |
| author={Kanishk Gandhi and Denise Lee and Gabriel Grand and Muxin Liu and Winson Cheng and Archit Sharma and Noah D. Goodman}, |
| year={2024}, |
| eprint={2404.03683}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.LG}, |
| url={https://huggingface.co/papers/2404.03683}, |
| } |
| |
| @misc{shao2024deepseekmathpushinglimitsmathematical, |
| title={DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}, |
| author={Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Xiao Bi and Haowei Zhang and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, |
| year={2024}, |
| eprint={2402.03300}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL}, |
| url={https://huggingface.co/papers/2402.03300}, |
| } |
| |
| @misc{deepseekai2025deepseekr1incentivizingreasoningcapability, |
| title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, |
| author={DeepSeek-AI and Daya Guo and Dejian Yang and Haowei Zhang and Junxiao Song and Ruoyu Zhang and Runxin Xu and Qihao Zhu and Shirong Ma and Peiyi Wang and Xiao Bi and Xiaokang Zhang and Xingkai Yu and Yu Wu and Z. F. Wu and Zhibin Gou and Zhihong Shao and Zhuoshu Li and Ziyi Gao and Aixin Liu and Bing Xue and Bingxuan Wang and Bochao Wu and Bei Feng and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fucong Dai and Fuli Luo and Guangbo Hao and Guanting Chen and Guowei Li and H. Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Qu and Hui Li and Jianzhong Guo and Jiashi Li and Jiawei Wang and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and J. L. Cai and Jiaqi Ni and Jian Liang and Jin Chen and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Liang Zhao and Litong Wang and Liyue Zhang and Lei Xu and Leyi Xia and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Meng Li and Miaojun Wang and Mingming Li and Ning Tian and Panpan Huang and Peng Zhang and Qiancheng Wang and Qinyu Chen and Qiushi Du and Ruiqi Ge and Ruisong Zhang and Ruizhe Pan and Runji Wang and R. J. Chen and R. L. Jin and Ruyi Chen and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shengfeng Ye and Shiyu Wang and Shuiping Yu and Shunfeng Zhou and Shuting Pan and S. S. Li and Shuang Zhou and Shaoqing Wu and Shengfeng Ye and Tao Yun and Tian Pei and Tianyu Sun and T. Wang and Wangding Zeng and Wanjia Zhao and Wen Liu and Wenfeng Liang and Wenjun Gao and Wenqin Yu and Wentao Zhang and W. L. Xiao and Wei An and Xiaodong Liu and Xiaohan Wang and Xiaokang Chen and Xiaotao Nie and Xin Cheng and Xin Liu and Xin Xie and Xingchao Liu and Xinyu Yang and Xinyuan Li and Xuecheng Su and Xuheng Lin and X. Q. Li and Xiangyue Jin and Xiaojin Shen and Xiaosha Chen and Xiaowen Sun and Xiaoxiang Wang and Xinnan Song and Xinyi Zhou and Xianzu Wang and Xinxia Shan and Y. K. Li and Y. Q. Wang and Y. X. Wei and Yang Zhang and Yanhong Xu and Yao Li and Yao Zhao and Yaofeng Sun and Yaohui Wang and Yi Yu and Yichao Zhang and Yifan Shi and Yiliang Xiong and Ying He and Yishi Piao and Yisong Wang and Yixuan Tan and Yiyang Ma and Yiyuan Liu and Yongqiang Guo and Yuan Ou and Yuduan Wang and Yue Gong and Yuheng Zou and Yujia He and Yunfan Xiong and Yuxiang Luo and Yuxiang You and Yuxuan Liu and Yuyang Zhou and Y. X. Zhu and Yanhong Xu and Yanping Huang and Yaohui Li and Yi Zheng and Yuchen Zhu and Yunxian Ma and Ying Tang and Yukun Zha and Yuting Yan and Z. Z. Ren and Zehui Ren and Zhangli Sha and Zhe Fu and Zhean Xu and Zhenda Xie and Zhengyan Zhang and Zhewen Hao and Zhicheng Ma and Zhigang Yan and Zhiyu Wu and Zihui Gu and Zijia Zhu and Zijun Liu and Zilin Li and Ziwei Xie and Ziyang Song and Zizheng Pan and Zhen Huang and Zhipeng Xu and Zhongyu Zhang and Zhen Zhang}, |
| year={2025}, |
| eprint={2501.12948}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL}, |
| url={https://huggingface.co/papers/2501.12948}, |
| } |
| |
| @misc{yang2025qwen3technicalreport, |
| title={Qwen3 Technical Report}, |
| author={An Yang and Anfeng Li and Baosong Yang and Beichen Zhang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Gao and Chengen Huang and Chenxu Lv and Chujie Zheng and Dayiheng Liu and Fan Zhou and Fei Huang and Feng Hu and Hao Ge and Haoran Wei and Huan Lin and Jialong Tang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Yang and Jiaxi Yang and Jing Zhou and Jingren Zhou and Junyang Lin and Kai Dang and Keqin Bao and Kexin Yang and Le Yu and Lianghao Deng and Mei Li and Mingfeng Xue and Mingze Li and Pei Zhang and Peng Wang and Qin Zhu and Rui Men and Ruize Gao and Shixuan Liu and Shuang Luo and Tianhao Li and Tianyi Tang and Wenbiao Yin and Xingzhang Ren and Xinyu Wang and Xinyu Zhang and Xuancheng Ren and Yang Fan and Yang Su and Yichang Zhang and Yinger Zhang and Yu Wan and Yuqiong Liu and Zekun Wang and Zeyu Cui and Zhenru Zhang and Zhipeng Zhou and Zihan Qiu}, |
| year={2025}, |
| eprint={2505.09388}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL}, |
| url={https://huggingface.co/papers/2505.09388}, |
| } |