Brown, T. And others. Language models are few learners. ADV. Nervousness. practical. split. 331877-1901 (2020).
Trinh, th, wu, y., le, QV, He, H. & Luong, T. Solving Olympiad Heygetry without human demonstrations. nature 625476-482 (2024).
The scientific researcher from Google
To me, j. And others. Getting the code at the level of competition with AlPhacode. sciences 3781092-1097 (2022).
The scientific researcher from Google
Yang, c. And others. SWE-Agent: Computer Software Engineering allows mechanism. in ADV. Nervousness. practical. split. 37 (NeuPIPs, 2024).
Khattab, O. et al. DSPY: Collecting the introductory language model calls for modern pipelines. in The twelfth international conference on learning representations (2024).
Zhaaria, M. Et al. Transformation from models to vehicle AI systems. Bayer https://bair.berkeleg (2024).
Zhou, y. et al. Big language models are engineers directed at the human level. in The eleventh international conference on learning representations (2023).
Krizhevsky, A., Sutskever, I. & Hinton, GE Imagenet Classification with Deep Tunus Neural Networks. in ADV. Nervousness. practical. split. 25 (Neurips, 2012).
Jumper, J. et al. Predicting with a very accurate protein structure with alphafold. nature 596583-589 (2021).
The scientific researcher from Google
Fawzi, A. Et al. Discovering double -rated algorithms faster with reinforcement learning. nature 61047-53 (2022).
The scientific researcher from Google
Mankowitz, Dj Et al. Faster sorting algorithms discovered using deep reinforcement learning. nature 618257-263 (2023).
The scientific researcher from Google
The merchant, a. And others. Deep learning limiting to discover materials. nature 62480-85 (2023).
The scientific researcher from Google
Goodfellow, I., Bengio, Y. & Couourville, A. Deep learning (With Journalism, 2016).
Rumelhart, De, Hinton, Ge & Williams, RJ Learning representations through decline errors. nature 323533-536 (1986).
The scientific researcher from Google
Brezant, R. And others. Automatic directed improvement with “gradient” and searching for a beam. in Brook. 2023 Conference on Experimental Methods in Treating Natural Language (Eds Bouamor, H. Et Al
Zheng, L. et al. Llm-AS-A-Dugy with MH-Bencer and Chatbot Arena. ADV. Nervousness. practical. split. 3646595-46623 (2023).
Li, x. et al. Alpacaeval: Automatic Restriction of Instruction Models. Gyrroup https://github.com/tatsu-lab/alpaca_eval (2023).
Bay, j. And others. Useful and harmless assistant training with learning to enhance human reactions. Preprint in https://arxiv.org/abs/2204.05862 (2022).
Madaan, A. Et al. Self -reverse: repetitive improvement with self -nutrition. in ADV. Nervousness. practical. split. 36 (NEUPS, 2023).
Stiennon, N. Et al. Learn to summarize with human reactions. A ADV. Nervousness. practical. split. 333008-3021 (2020).
Yuan, W. and others. Language models that are good at the self. in The forty -first international conference on machine learning (2024).
Dubois, y. et al. Alpacafarm: Simulating frameworks that learn from human reactions. in ADV. Nervousness. practical. split. 36 (NEUPS, 2023).
Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K. & Yao, S. ADV. Nervousness. practical. split. 368634-8652 (2023).
Rin, d. And others. GPQA: Standard of Questions and Resistant Answers at the level of graduates. in The first conference of language modeling (2024).
Hendrycks, D. et al. Measuring the understanding of a massive multi -task language. in The ninth international conference on learning representations (2021).
Lu, b. And others. Mathvista: Evaluating mathematical thinking of the basic models in visual contexts. in The twelfth international conference on learning representations (2024).
Lu, b. And others. Learn to explain: multimedia thinking through thought chains to answer science questions. ADV. Nervousness. practical. split. 352507-2521 (2022).
LIU, p. et al. Pre -training, claim, and prediction: a systematic survey of methods of methods in treating natural language. ACM Comput. Survival. 551-35 (2023).
The scientific researcher from Google
Suzgun, M. Et al. Challenging great tasks in the large term and whether the idea series can be solved. in Results of the Association of Mass: ACL 2023 13003-13051 (Association of Mass, 2023).
Cobbe, K. et al. Training challenges to solve mathematics lyric problems. Preprint in https://arxiv.org/abs/2110.14168 (2021).
Yang, C and others. Great language models as improved. in The twelfth international conference on learning representations (2024).
Dubey, A. Et al. Lama cap 3 of the models. Preprint in https://arxiv.org/abs/2407.21783 (2024).
Yang, a. And others. QWEN2 Technical Report. Preprint in https://arxiv.org/abs/2407.10671 (2024).
Khan, FM, Gibbons, JP & Spertuto, PW Planning of Khan treatment in radiology (Lippincott Williams & Wilkins (Wolters Kluweer), 2016).
Hussein, M. Br. J. Radiol. 9120180270 (2018).
The scientific researcher from Google
Kisling, K. et al. Radiation Planning Assistant, A, fully automated radiotherapy system. J. Vis. Earn. 134E57411 (2018).
Huang, C., Nomura, Y., Yang, Y. & Xing, L. Meta-Optimization for completely automated radiotherapy. physics. Med. Biol. 67055011 (2022).
The scientific researcher from Google
Yang, Y. & Xing, L. Clinical Clinical Roverse Treatment Planning. physics. Med. Biol. 495101 (2004).
The scientific researcher from Google
Liu, S. Et al. Automatic radiotherapy layout is guided by GPT-4vision. Preprint in https://arxiv.org/abs/2406.15609 (2024).
Lu, b. And others. Charmeleon: The syntactic logic of delivery and operation with large language models. ADV. Nervousness. practical. split. 3643447-43478 (2023).
Yan, b. , Chang, c. Yuan, g. Preprint in https://arxiv.org/abs/2406.17115 (2024).
Wei, J. et al. The series of idea that provokes thinking about large language models. ADV. Nervousness. practical. split. 3524824-24837 (2022).
Bottou, L. Automatic learning widely with random gradient. in Brook. Compststat’2010 (Eds Lechevallier, Y. & Saporta, G.) 177–186 (Physica-Verlag, 2010).
Wang, S. And others. High -dimensional automated radiotherapy planning by improving Paisi. Med. physics. 503773-3787 (2023).
The scientific researcher from Google
Akiba, T., Sano, S., Yanase, T., OHTA, T in Brook. ACM Sigkdd Fifth International Conference to discover knowledge and extract data (2019).
Pianchi, F. And others. Closed Group / Vital text: V0.1.6. Zenudo https://doi.org/10.5281/zenodo.14497017 (2024).