Zobrazeno 1 - 10
of 86
pro vyhledávání: '"FURUTA, Hiroki"'
Autor:
Furuta, Hiroki, Lee, Kuang-Huei, Gu, Shixiang Shane, Matsuo, Yutaka, Faust, Aleksandra, Zen, Heiga, Gur, Izzeddin
Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, it is reasonable to think that they can vary with different individuals, and thus should be distributional to reflect the fi
Externí odkaz:
http://arxiv.org/abs/2409.06691
Grokking has been actively explored to reveal the mystery of delayed generalization. Identifying interpretable algorithms inside the grokked models is a suggestive hint to understanding its mechanism. In this work, beyond the simplest and well-studie
Externí odkaz:
http://arxiv.org/abs/2402.16726
Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs. To address these limitations, we propose ReadAgent, an LLM agent system that increases effective context
Externí odkaz:
http://arxiv.org/abs/2402.09727
Language model agents (LMA) recently emerged as a promising paradigm on muti-step decision making tasks, often outperforming humans and other reinforcement learning agents. Despite the promise, their performance on real-world applications that often
Externí odkaz:
http://arxiv.org/abs/2311.18751
Autor:
Collaboration, Open X-Embodiment, O'Neill, Abby, Rehman, Abdul, Gupta, Abhinav, Maddukuri, Abhiram, Gupta, Abhishek, Padalkar, Abhishek, Lee, Abraham, Pooley, Acorn, Gupta, Agrim, Mandlekar, Ajay, Jain, Ajinkya, Tung, Albert, Bewley, Alex, Herzog, Alex, Irpan, Alex, Khazatsky, Alexander, Rai, Anant, Gupta, Anchit, Wang, Andrew, Kolobov, Andrey, Singh, Anikait, Garg, Animesh, Kembhavi, Aniruddha, Xie, Annie, Brohan, Anthony, Raffin, Antonin, Sharma, Archit, Yavary, Arefeh, Jain, Arhan, Balakrishna, Ashwin, Wahid, Ayzaan, Burgess-Limerick, Ben, Kim, Beomjoon, Schölkopf, Bernhard, Wulfe, Blake, Ichter, Brian, Lu, Cewu, Xu, Charles, Le, Charlotte, Finn, Chelsea, Wang, Chen, Xu, Chenfeng, Chi, Cheng, Huang, Chenguang, Chan, Christine, Agia, Christopher, Pan, Chuer, Fu, Chuyuan, Devin, Coline, Xu, Danfei, Morton, Daniel, Driess, Danny, Chen, Daphne, Pathak, Deepak, Shah, Dhruv, Büchler, Dieter, Jayaraman, Dinesh, Kalashnikov, Dmitry, Sadigh, Dorsa, Johns, Edward, Foster, Ethan, Liu, Fangchen, Ceola, Federico, Xia, Fei, Zhao, Feiyu, Frujeri, Felipe Vieira, Stulp, Freek, Zhou, Gaoyue, Sukhatme, Gaurav S., Salhotra, Gautam, Yan, Ge, Feng, Gilbert, Schiavi, Giulio, Berseth, Glen, Kahn, Gregory, Yang, Guangwen, Wang, Guanzhi, Su, Hao, Fang, Hao-Shu, Shi, Haochen, Bao, Henghui, Amor, Heni Ben, Christensen, Henrik I, Furuta, Hiroki, Bharadhwaj, Homanga, Walke, Homer, Fang, Hongjie, Ha, Huy, Mordatch, Igor, Radosavovic, Ilija, Leal, Isabel, Liang, Jacky, Abou-Chakra, Jad, Kim, Jaehyung, Drake, Jaimyn, Peters, Jan, Schneider, Jan, Hsu, Jasmine, Vakil, Jay, Bohg, Jeannette, Bingham, Jeffrey, Wu, Jeffrey, Gao, Jensen, Hu, Jiaheng, Wu, Jiajun, Wu, Jialin, Sun, Jiankai, Luo, Jianlan, Gu, Jiayuan, Tan, Jie, Oh, Jihoon, Wu, Jimmy, Lu, Jingpei, Yang, Jingyun, Malik, Jitendra, Silvério, João, Hejna, Joey, Booher, Jonathan, Tompson, Jonathan, Yang, Jonathan, Salvador, Jordi, Lim, Joseph J., Han, Junhyek, Wang, Kaiyuan, Rao, Kanishka, Pertsch, Karl, Hausman, Karol, Go, Keegan, Gopalakrishnan, Keerthana, Goldberg, Ken, Byrne, Kendra, Oslund, Kenneth, Kawaharazuka, Kento, Black, Kevin, Lin, Kevin, Zhang, Kevin, Ehsani, Kiana, Lekkala, Kiran, Ellis, Kirsty, Rana, Krishan, Srinivasan, Krishnan, Fang, Kuan, Singh, Kunal Pratap, Zeng, Kuo-Hao, Hatch, Kyle, Hsu, Kyle, Itti, Laurent, Chen, Lawrence Yunliang, Pinto, Lerrel, Fei-Fei, Li, Tan, Liam, Fan, Linxi "Jim", Ott, Lionel, Lee, Lisa, Weihs, Luca, Chen, Magnum, Lepert, Marion, Memmel, Marius, Tomizuka, Masayoshi, Itkina, Masha, Castro, Mateo Guaman, Spero, Max, Du, Maximilian, Ahn, Michael, Yip, Michael C., Zhang, Mingtong, Ding, Mingyu, Heo, Minho, Srirama, Mohan Kumar, Sharma, Mohit, Kim, Moo Jin, Kanazawa, Naoaki, Hansen, Nicklas, Heess, Nicolas, Joshi, Nikhil J, Suenderhauf, Niko, Liu, Ning, Di Palo, Norman, Shafiullah, Nur Muhammad Mahi, Mees, Oier, Kroemer, Oliver, Bastani, Osbert, Sanketi, Pannag R, Miller, Patrick "Tree", Yin, Patrick, Wohlhart, Paul, Xu, Peng, Fagan, Peter David, Mitrano, Peter, Sermanet, Pierre, Abbeel, Pieter, Sundaresan, Priya, Chen, Qiuyu, Vuong, Quan, Rafailov, Rafael, Tian, Ran, Doshi, Ria, Mart'in-Mart'in, Roberto, Baijal, Rohan, Scalise, Rosario, Hendrix, Rose, Lin, Roy, Qian, Runjia, Zhang, Ruohan, Mendonca, Russell, Shah, Rutav, Hoque, Ryan, Julian, Ryan, Bustamante, Samuel, Kirmani, Sean, Levine, Sergey, Lin, Shan, Moore, Sherry, Bahl, Shikhar, Dass, Shivin, Sonawani, Shubham, Tulsiani, Shubham, Song, Shuran, Xu, Sichun, Haldar, Siddhant, Karamcheti, Siddharth, Adebola, Simeon, Guist, Simon, Nasiriany, Soroush, Schaal, Stefan, Welker, Stefan, Tian, Stephen, Ramamoorthy, Subramanian, Dasari, Sudeep, Belkhale, Suneel, Park, Sungjae, Nair, Suraj, Mirchandani, Suvir, Osa, Takayuki, Gupta, Tanmay, Harada, Tatsuya, Matsushima, Tatsuya, Xiao, Ted, Kollar, Thomas, Yu, Tianhe, Ding, Tianli, Davchev, Todor, Zhao, Tony Z., Armstrong, Travis, Darrell, Trevor, Chung, Trinity, Jain, Vidhi, Kumar, Vikash, Vanhoucke, Vincent, Zhan, Wei, Zhou, Wenxuan, Burgard, Wolfram, Chen, Xi, Chen, Xiangyu, Wang, Xiaolong, Zhu, Xinghao, Geng, Xinyang, Liu, Xiyuan, Liangwei, Xu, Li, Xuanlin, Pang, Yansong, Lu, Yao, Ma, Yecheng Jason, Kim, Yejin, Chebotar, Yevgen, Zhou, Yifan, Zhu, Yifeng, Wu, Yilin, Xu, Ying, Wang, Yixuan, Bisk, Yonatan, Dou, Yongqiang, Cho, Yoonyoung, Lee, Youngwoon, Cui, Yuchen, Cao, Yue, Wu, Yueh-Hua, Tang, Yujin, Zhu, Yuke, Zhang, Yunchu, Jiang, Yunfan, Li, Yunshuang, Li, Yunzhu, Iwasawa, Yusuke, Matsuo, Yutaka, Ma, Zehan, Xu, Zhuo, Cui, Zichen Jeff, Zhang, Zichen, Fu, Zipeng, Lin, Zipeng
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretra
Externí odkaz:
http://arxiv.org/abs/2310.08864
Autor:
Gur, Izzeddin, Furuta, Hiroki, Huang, Austin, Safdari, Mustafa, Matsuo, Yutaka, Eck, Douglas, Faust, Aleksandra
Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world websites has still suffered from (1) open domainness, (2) limited context
Externí odkaz:
http://arxiv.org/abs/2307.12856
Autor:
Furuta, Hiroki, Lee, Kuang-Huei, Nachum, Ofir, Matsuo, Yutaka, Faust, Aleksandra, Gu, Shixiang Shane, Gur, Izzeddin
The progress of autonomous web navigation has been hindered by the dependence on billions of exploratory interactions via online reinforcement learning, and domain-specific model designs that make it difficult to leverage generalization from rich out
Externí odkaz:
http://arxiv.org/abs/2305.11854
Autor:
Kuroki, So, Matsushima, Tatsuya, Arima, Jumpei, Furuta, Hiroki, Matsuo, Yutaka, Gu, Shixiang Shane, Tang, Yujin
While natural systems often present collective intelligence that allows them to self-organize and adapt to changes, the equivalent is missing in most artificial systems. We explore the possibility of such a system in the context of cooperative 2D pus
Externí odkaz:
http://arxiv.org/abs/2211.15136
The rise of generalist large-scale models in natural language and vision has made us expect that a massive data-driven approach could achieve broader generalization in other domains such as continuous control. In this work, we explore a method for le
Externí odkaz:
http://arxiv.org/abs/2211.14296
How to extract as much learning signal from each trajectory data has been a key problem in reinforcement learning (RL), where sample inefficiency has posed serious challenges for practical applications. Recent works have shown that using expressive p
Externí odkaz:
http://arxiv.org/abs/2111.10364