ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

Autor: Chen, Ziru, Chen, Shijie, Ning, Yuting, Zhang, Qianheng, Wang, Boshi, Yu, Botao, Li, Yifei, Liao, Zeyi, Wei, Chen, Lu, Zitong, Dey, Vishal, Xue, Mingyi, Baker, Frazier N., Burns, Benjamin, Adu-Ampratwum, Daniel, Huang, Xuhui, Ning, Xia, Gao, Song, Su, Yu, Sun, Huan

The advancements of language language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true capabilities. In t

Externí odkaz: http://arxiv.org/abs/2410.05080

The Giant Radio Array for Neutrino Detection (GRAND) Collaboration -- Contributions to the 10th International Workshop on Acoustic and Radio EeV Neutrino Detection Activities (ARENA 2024)

Autor: Batista, Rafael Alves, Benoit-Lévy, Aurélien, Bister, Teresa, Bohacova, Martina, Bustamante, Mauricio, Carvalho, Washington, Chen, Yiren, Cheng, LingMei, Chiche, Simon, Colley, Jean-Marc, Correa, Pablo, Laurenciu, Nicoleta Cucu, Dai, Zigao, de Almeida, Rogerio M., de Errico, Beatriz, de Jong, Sijbrand, Neto, João R. T. de Mello, de Vries, Krijn D, Decoene, Valentin, Denton, Peter B., Duan, Bohao, Duan, Kaikai, Engel, Ralph, Erba, William, Fan, Yizhong, Ferrière, Arsène, Gou, QuanBu, Gu, Junhua, Guelfand, Marion, Guo, Jianhua, Guo, Yiqing, Guépin, Claire, Gülzow, Lukas, Haungs, Andreas, Havelka, Matej, He, Haoning, Hivon, Eric, Hu, Hongbo, Huang, Xiaoyuan, Huang, Yan, Huege, Tim, Jiang, Wen, Koirala, Ramesh, Kong, ChuiZheng, Kotera, Kumiko, Köhler, Jelena, Lago, Bruno L., Lai, Zhisen, Coz, Sandra Le, Legrand, François, Leisos, Antonios, Li, Rui, Li, Xingyu, Li, YiFei, Liu, Cheng, Liu, Ruoyu, Liu, Wei, Ma, Pengxiong, Macias, Oscar, Magnard, Frédéric, Marcowith, Alexandre, Martineau-Huynh, Olivier, McKinley, Thomas, Minodier, Paul, Mitra, Pragati, Mostafá, Miguel, Murase, Kohta, Niess, Valentin, Nonis, Stavros, Ogio, Shoichi, Oikonomou, Foteini, Pan, Hongwei, Papageorgiou, Konstantinos, Pierog, Tanguy, Piotrowski, Lech Wiktor, Prunet, Simon, Qian, Xiangli, Roth, Markus, Sako, Takashi, Schoorlemmer, Harm, Szálas-Motesiczky, Dániel, Sławiński, Szymon, Tian, Xishui, Timmermans, Anne, Timmermans, Charles, Tobiska, Petr, Tsirigotis, Apostolos, Tueros, Matías, Vittakis, George, Wang, Hanrui, Wang, Jiale, Wang, Shen, Wang, Xiangyu, Wang, Xu, Wei, Daming, Wei, Feng, Wu, Xiangping, Wu, Xuefeng, Xu, Xin, Xu, Xing, Yang, Fufu, Yang, Lili, Yang, Xuan, Yuan, Qiang, Zarka, Philippe, Zeng, Houdun, Zhang, Chao, Zhang, Jianli, Zhang, Kewen, Zhang, Pengfei, Zhang, Qingchi, Zhang, Songbo, Zhang, Yi, Zhou, Hao, Wissel, Stephanie, Zeolla, Andrew, Deaconu, Cosmin, Hughes, Kaeli, Martin, Zachary, Mulrey, Katharine, Cummings, Austin, Krömer, Oliver, Plant, Kathryn, Schroeder, Frank G.

This is an index of the contributions by the Giant Radio Array for Neutrino Detection (GRAND) Collaboration to the 10th International Workshop on Acoustic and Radio EeV Neutrino Detection Activities (ARENA 2024, University of Chicago, June 11-14, 202

Externí odkaz: http://arxiv.org/abs/2409.03427

Homology of Segre powers of Boolean and subspace lattices

Autor: Li, Yifei, Sundaram, Sheila

Segre products of posets were defined by Bj\"orner and Welker [J. Pure Appl. Algebra, 198(1-3), 43--55 (2005)]. We investigate the $t$-fold Segre powers of the Boolean lattice $B_n$ and the subspace lattice $B_n(q)$. The case $t=2$ was considered by

Externí odkaz: http://arxiv.org/abs/2408.08421

Learning Physical Simulation with Message Passing Transformer

Autor: Xu, Zeyi, Li, Yifei

Machine learning methods for physical simulation have achieved significant success in recent years. We propose a new universal architecture based on Graph Neural Network, the Message Passing Transformer, which incorporates a Message Passing framework

Externí odkaz: http://arxiv.org/abs/2406.06060

Neural Fluidic System Design and Control with Differentiable Simulation

Autor: Li, Yifei, Sun, Yuchen, Ma, Pingchuan, Sifakis, Eftychios, Du, Tao, Zhu, Bo, Matusik, Wojciech

We present a novel framework to explore neural control and design of complex fluidic systems with dynamic solid boundaries. Our system features a fast differentiable Navier-Stokes solver with solid-fluid interface handling, a low-dimensional differen

Externí odkaz: http://arxiv.org/abs/2405.14903