Zobrazeno 1 - 10
of 515
pro vyhledávání: '"Li Ryan"'
Federated training methods have gained popularity for graph learning with applications including friendship graphs of social media sites and customer-merchant interaction graphs of huge online marketplaces. However, privacy regulations often require
Externí odkaz:
http://arxiv.org/abs/2412.16144
Sketches are a natural and accessible medium for UI designers to conceptualize early-stage ideas. However, existing research on UI/UX automation often requires high-fidelity inputs like Figma designs or detailed screenshots, limiting accessibility an
Externí odkaz:
http://arxiv.org/abs/2410.16232
While large language models (LLMs) have rapidly improved their performance on a broad number of tasks, they still often fall short on reasoning tasks. As LLMs become more integrated in diverse real-world tasks, advancing their reasoning capabilities
Externí odkaz:
http://arxiv.org/abs/2410.07839
Autor:
Shi, Weiyan, Li, Ryan, Zhang, Yutong, Ziems, Caleb, yu, Chunhua, Horesh, Raya, de Paula, Rogério Abreu, Yang, Diyi
To enhance language models' cultural awareness, we design a generalizable pipeline to construct cultural knowledge bases from different online communities on a massive scale. With the pipeline, we construct CultureBank, a knowledge base built upon us
Externí odkaz:
http://arxiv.org/abs/2404.15238
Generative AI has made rapid advancements in recent years, achieving unprecedented capabilities in multimodal understanding and code generation. This can enable a new paradigm of front-end development in which multimodal large language models (MLLMs)
Externí odkaz:
http://arxiv.org/abs/2403.03163
Autor:
King, Andrew D., Nocera, Alberto, Rams, Marek M., Dziarmaga, Jacek, Wiersema, Roeland, Bernoudy, William, Raymond, Jack, Kaushal, Nitin, Heinsdorf, Niclas, Harris, Richard, Boothby, Kelly, Altomare, Fabio, Berkley, Andrew J., Boschnak, Martin, Chern, Kevin, Christiani, Holly, Cibere, Samantha, Connor, Jake, Dehn, Martin H., Deshpande, Rahul, Ejtemaee, Sara, Farré, Pau, Hamer, Kelsey, Hoskinson, Emile, Huang, Shuiyuan, Johnson, Mark W., Kortas, Samuel, Ladizinsky, Eric, Lai, Tony, Lanting, Trevor, Li, Ryan, MacDonald, Allison J. R., Marsden, Gaelen, McGeoch, Catherine C., Molavi, Reza, Neufeld, Richard, Norouzpour, Mana, Oh, Travis, Pasvolsky, Joel, Poitras, Patrick, Poulin-Lamarre, Gabriel, Prescott, Thomas, Reis, Mauricio, Rich, Chris, Samani, Mohammad, Sheldan, Benjamin, Smirnov, Anatoly, Sterpka, Edward, Clavera, Berta Trullas, Tsai, Nicholas, Volkmann, Mark, Whiticar, Alexander, Whittaker, Jed D., Wilkinson, Warren, Yao, Jason, Yi, T. J., Sandvik, Anders W., Alvarez, Gonzalo, Melko, Roger G., Carrasquilla, Juan, Franz, Marcel, Amin, Mohammad H.
Quantum computers hold the promise of solving certain problems that lie beyond the reach of conventional computers. Establishing this capability, especially for impactful and meaningful problems, remains a central challenge. One such problem is the s
Externí odkaz:
http://arxiv.org/abs/2403.00910
In this work, we examine how fact-checkers prioritize which claims to fact-check and what tools may assist them in their efforts. Through a series of interviews with 23 professional fact-checkers from around the world, we validate that harm assessmen
Externí odkaz:
http://arxiv.org/abs/2312.11678
Publikováno v:
IEEE Visualization Conference NLVIZ Workshop 2022
We develop NL2INTERFACE to explore the potential of generating usable interactive multi-visualization interfaces from natural language queries. With NL2INTERFACE, users can directly write natural language queries to automatically generate a fully int
Externí odkaz:
http://arxiv.org/abs/2209.08834
Cloud processes are the largest source of uncertainty in quantifying the global temperature response to carbon dioxide rise. Still, the role of precipitation efficiency (PE) -- surface rain per unit column -- integrated condensation -- is yet to be q
Externí odkaz:
http://arxiv.org/abs/2207.06188