Zobrazeno 1 - 10
of 1 043
pro vyhledávání: '"Hejna, P."'
Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language processing, little
Externí odkaz:
http://arxiv.org/abs/2408.14037
Autor:
Dziubański, Jacek, Hejna, Agnieszka
Let $\{P_t\}_{t>0}$ be the Dunkl-Poisson semigroup associated with a root system $R\subset \mathbb R^N$ and a multiplicity function $k\geq 0$. Analogously to the classical theory, we say that a bounded measurable function $f$ defined on $\mathbb R^N$
Externí odkaz:
http://arxiv.org/abs/2408.12399
Autor:
Rafailov, Rafael, Chittepu, Yaswanth, Park, Ryan, Sikchi, Harshit, Hejna, Joey, Knox, Bradley, Finn, Chelsea, Niekum, Scott
Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs), however, it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained to represen
Externí odkaz:
http://arxiv.org/abs/2406.02900
Autor:
Bao, Yujia, Shah, Ankit Parag, Narang, Neeru, Rivers, Jonathan, Maksey, Rajeev, Guan, Lan, Barrere, Louise N., Evenson, Shelley, Basole, Rahul, Miao, Connie, Mehta, Ankit, Boulay, Fabien, Park, Su Min, Pearson, Natalie E., Joy, Eldhose, He, Tiger, Thakur, Sumiran, Ghosal, Koustav, On, Josh, Morrison, Phoebe, Major, Tim, Wang, Eva Siqi, Escobar, Gina, Wei, Jiaheng, Weerasooriya, Tharindu Cyril, Song, Queena, Lashkevich, Daria, Chen, Clare, Kim, Gyuhak, Yin, Dengpan, Hejna, Don, Nomeli, Mo, Wei, Wei
This paper introduces Fortune Analytics Language Model (FALM). FALM empowers users with direct access to comprehensive business analysis, including market trends, company performance metrics, and expert insights. Unlike generic LLMs, FALM leverages a
Externí odkaz:
http://arxiv.org/abs/2406.06559
Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires prohibitively large
Externí odkaz:
http://arxiv.org/abs/2406.00888
Autor:
Octo Model Team, Ghosh, Dibya, Walke, Homer, Pertsch, Karl, Black, Kevin, Mees, Oier, Dasari, Sudeep, Hejna, Joey, Kreiman, Tobias, Xu, Charles, Luo, Jianlan, Tan, You Liang, Chen, Lawrence Yunliang, Sanketi, Pannag, Vuong, Quan, Xiao, Ted, Sadigh, Dorsa, Finn, Chelsea, Levine, Sergey
Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies may be finetuned with only a little in-domain data, yet generalize bro
Externí odkaz:
http://arxiv.org/abs/2405.12213
Reinforcement Learning From Human Feedback (RLHF) has been critical to the success of the latest generation of generative AI models. In response to the complex nature of the classical RLHF pipeline, direct alignment algorithms such as Direct Preferen
Externí odkaz:
http://arxiv.org/abs/2404.12358
Autor:
Khazatsky, Alexander, Pertsch, Karl, Nair, Suraj, Balakrishna, Ashwin, Dasari, Sudeep, Karamcheti, Siddharth, Nasiriany, Soroush, Srirama, Mohan Kumar, Chen, Lawrence Yunliang, Ellis, Kirsty, Fagan, Peter David, Hejna, Joey, Itkina, Masha, Lepert, Marion, Ma, Yecheng Jason, Miller, Patrick Tree, Wu, Jimmy, Belkhale, Suneel, Dass, Shivin, Ha, Huy, Jain, Arhan, Lee, Abraham, Lee, Youngwoon, Memmel, Marius, Park, Sungjae, Radosavovic, Ilija, Wang, Kaiyuan, Zhan, Albert, Black, Kevin, Chi, Cheng, Hatch, Kyle Beltran, Lin, Shan, Lu, Jingpei, Mercat, Jean, Rehman, Abdul, Sanketi, Pannag R, Sharma, Archit, Simpson, Cody, Vuong, Quan, Walke, Homer Rich, Wulfe, Blake, Xiao, Ted, Yang, Jonathan Heewon, Yavary, Arefeh, Zhao, Tony Z., Agia, Christopher, Baijal, Rohan, Castro, Mateo Guaman, Chen, Daphne, Chen, Qiuyu, Chung, Trinity, Drake, Jaimyn, Foster, Ethan Paul, Gao, Jensen, Herrera, David Antonio, Heo, Minho, Hsu, Kyle, Hu, Jiaheng, Jackson, Donovon, Le, Charlotte, Li, Yunshuang, Lin, Kevin, Lin, Roy, Ma, Zehan, Maddukuri, Abhiram, Mirchandani, Suvir, Morton, Daniel, Nguyen, Tony, O'Neill, Abigail, Scalise, Rosario, Seale, Derick, Son, Victor, Tian, Stephen, Tran, Emi, Wang, Andrew E., Wu, Yilin, Xie, Annie, Yang, Jingyun, Yin, Patrick, Zhang, Yunchu, Bastani, Osbert, Berseth, Glen, Bohg, Jeannette, Goldberg, Ken, Gupta, Abhinav, Gupta, Abhishek, Jayaraman, Dinesh, Lim, Joseph J, Malik, Jitendra, Martín-Martín, Roberto, Ramamoorthy, Subramanian, Sadigh, Dorsa, Song, Shuran, Wu, Jiajun, Yip, Michael C., Zhu, Yuke, Kollar, Thomas, Levine, Sergey, Finn, Chelsea
The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. However, creating such datasets is challenging: collecting robot manipul
Externí odkaz:
http://arxiv.org/abs/2403.12945
Autor:
Hejna, Joey, Rafailov, Rafael, Sikchi, Harshit, Finn, Chelsea, Niekum, Scott, Knox, W. Bradley, Sadigh, Dorsa
Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second, align the
Externí odkaz:
http://arxiv.org/abs/2310.13639
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