Zobrazeno 1 - 10
of 286
pro vyhledávání: '"Yao, Andrew"'
We introduce Diagram of Thought (DoT), a framework that models iterative reasoning in large language models (LLMs) as the construction of a directed acyclic graph (DAG) within a single model. Unlike traditional approaches that represent reasoning as
Externí odkaz:
http://arxiv.org/abs/2409.10038
Autor:
Baum, Carsten, Berlips, Jens, Chen, Walther, Cui, Hongrui, Damgard, Ivan, Dong, Jiangbin, Esvelt, Kevin M., Foner, Leonard, Gao, Mingyu, Gretton, Dana, Kysel, Martin, Li, Juanru, Li, Xiang, Paneth, Omer, Rivest, Ronald L., Sage-Ling, Francesca, Shamir, Adi, Shen, Yue, Sun, Meicen, Vaikuntanathan, Vinod, Van Hauwe, Lynn, Vogel, Theia, Weinstein-Raun, Benjamin, Wang, Yun, Wichs, Daniel, Wooster, Stephen, Yao, Andrew C., Yu, Yu, Zhang, Haoling, Zhang, Kaiyi
Printing custom DNA sequences is essential to scientific and biomedical research, but the technology can be used to manufacture plagues as well as cures. Just as ink printers recognize and reject attempts to counterfeit money, DNA synthesizers and as
Externí odkaz:
http://arxiv.org/abs/2403.14023
To improve language models' proficiency in mathematical reasoning via continual pretraining, we introduce a novel strategy that leverages base language models for autonomous data selection. Departing from conventional supervised fine-tuning or traine
Externí odkaz:
http://arxiv.org/abs/2402.07625
Despite the advancements in large language models (LLMs) for mathematical reasoning, solving competition-level math problems remains a significant challenge, especially for open-source LLMs without external tools. We introduce the MMIQC dataset, comp
Externí odkaz:
http://arxiv.org/abs/2401.09003
In this work, we present a comprehensive study of Meta Prompting (MP), an innovative technique reshaping the utilization of language models (LMs) and AI systems in problem-solving and data interaction. Grounded in type theory and category theory, Met
Externí odkaz:
http://arxiv.org/abs/2311.11482
Autor:
Bengio, Yoshua, Hinton, Geoffrey, Yao, Andrew, Song, Dawn, Abbeel, Pieter, Darrell, Trevor, Harari, Yuval Noah, Zhang, Ya-Qin, Xue, Lan, Shalev-Shwartz, Shai, Hadfield, Gillian, Clune, Jeff, Maharaj, Tegan, Hutter, Frank, Baydin, Atılım Güneş, McIlraith, Sheila, Gao, Qiqi, Acharya, Ashwin, Krueger, David, Dragan, Anca, Torr, Philip, Russell, Stuart, Kahneman, Daniel, Brauner, Jan, Mindermann, Sören
Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increases in capabilities and autonomy may soon massively amplify AI's impact,
Externí odkaz:
http://arxiv.org/abs/2310.17688
Despite the recent advancements in language models (LMs), their ability to solve complex problems remains limited. This paper introduces Cumulative Reasoning (CR), a novel approach that utilizes LMs cumulatively and iteratively, mirroring human thoug
Externí odkaz:
http://arxiv.org/abs/2308.04371
Autor:
Yao, Andrew
Let $K$ be a global function field. Using Haar measures, we compute the densities of the Kodiara types and Tamagawa numbers of elliptic curves over a completion of $K$. Also, we prove results about the number of iterations of Tate's algorithm that ar
Externí odkaz:
http://arxiv.org/abs/2301.11437
Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression
One of the major open problems in machine learning is to characterize generalization in the overparameterized regime, where most traditional generalization bounds become inconsistent even for overparameterized linear regression. In many scenarios, th
Externí odkaz:
http://arxiv.org/abs/2202.06054
Autor:
Yao, Andrew
With operators on formal series in $x_i$, $1\leq i\leq N$, which are symmetric in $N-1$ of the $x_i$, probability measures can be studied through Bessel generating functions. These operators are used with the Dunkl transform on the Bessel generating
Externí odkaz:
http://arxiv.org/abs/2109.14052