Zobrazeno 1 - 10
of 6 520
pro vyhledávání: '"Brown Kevin"'
Autor:
Leyton-Brown, Kevin, Shoham, Yoav
Motivated by the rapid ascent of Large Language Models (LLMs) and debates about the extent to which they possess human-level qualities, we propose a framework for testing whether any agent (be it a machine or a human) understands a subject matter. In
Externí odkaz:
http://arxiv.org/abs/2406.10937
Multi-modal learning has significantly advanced generative AI, especially in vision-language modeling. Innovations like GPT-4V and open-source projects such as LLaVA have enabled robust conversational agents capable of zero-shot task completions. How
Externí odkaz:
http://arxiv.org/abs/2406.09454
Autor:
Graham, Devon, Leyton-Brown, Kevin
Utilitarian algorithm configuration is a general-purpose technique for automatically searching the parameter space of a given algorithm to optimize its performance, as measured by a given utility function, on a given set of inputs. Recently introduce
Externí odkaz:
http://arxiv.org/abs/2405.18246
Autor:
Prabhakar, Raghu, Sivaramakrishnan, Ram, Gandhi, Darshan, Du, Yun, Wang, Mingran, Song, Xiangyu, Zhang, Kejie, Gao, Tianren, Wang, Angela, Li, Karen, Sheng, Yongning, Brot, Joshua, Sokolov, Denis, Vivek, Apurv, Leung, Calvin, Sabnis, Arjun, Bai, Jiayu, Zhao, Tuowen, Gottscho, Mark, Jackson, David, Luttrell, Mark, Shah, Manish K., Chen, Edison, Liang, Kaizhao, Jain, Swayambhoo, Thakker, Urmish, Huang, Dawei, Jairath, Sumti, Brown, Kevin J., Olukotun, Kunle
Monolithic large language models (LLMs) like GPT-4 have paved the way for modern generative AI applications. Training, serving, and maintaining monolithic LLMs at scale, however, remains prohibitively expensive and challenging. The disproportionate i
Externí odkaz:
http://arxiv.org/abs/2405.07518
Autor:
Kuznetsov, Ilia, Afzal, Osama Mohammed, Dercksen, Koen, Dycke, Nils, Goldberg, Alexander, Hope, Tom, Hovy, Dirk, Kummerfeld, Jonathan K., Lauscher, Anne, Leyton-Brown, Kevin, Lu, Sheng, Mausam, Mieskes, Margot, Névéol, Aurélie, Pruthi, Danish, Qu, Lizhen, Schwartz, Roy, Smith, Noah A., Solorio, Thamar, Wang, Jingyan, Zhu, Xiaodan, Rogers, Anna, Shah, Nihar B., Gurevych, Iryna
The number of scientific articles produced every year is growing rapidly. Providing quality control over them is crucial for scientists and, ultimately, for the public good. In modern science, this process is largely delegated to peer review -- a dis
Externí odkaz:
http://arxiv.org/abs/2405.06563
Iterative combinatorial auctions are widely used in high stakes settings such as spectrum auctions. Such auctions can be hard to analyze, making it difficult for bidders to determine how to behave and for designers to optimize auction rules to ensure
Externí odkaz:
http://arxiv.org/abs/2402.19420
Autor:
Raman, Narun, Lundy, Taylor, Amouyal, Samuel, Levine, Yoav, Leyton-Brown, Kevin, Tennenholtz, Moshe
There is increasing interest in using LLMs as decision-making "agents." Doing so includes many degrees of freedom: which model should be used; how should it be prompted; should it be asked to introspect, conduct chain-of-thought reasoning, etc? Settl
Externí odkaz:
http://arxiv.org/abs/2402.09552
Mobile gaming is a rapidly growing and incredibly profitable sector; having grown seven-fold over the past 10 years, it now grosses over $100 billion annually. This growth was due in large part to a shift in monetization strategies: rather than charg
Externí odkaz:
http://arxiv.org/abs/2312.10205
We present the first nontrivial procedure for configuring heuristic algorithms to maximize the utility provided to their end users while also offering theoretical guarantees about performance. Existing procedures seek configurations that minimize exp
Externí odkaz:
http://arxiv.org/abs/2310.20401