Source-linked AI summary

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu, Toby Boyd, Brad Hekman, Aaron Parisi, Chaoyi Zhang, Kornraphop Kawintiranon, Tania Bedrax-Weiss, Oliver Wang, Ya Xu, Ollie Purkiss, Uri Mendlovic, Ilaï Deutel, Nam Nguyen, Adam Langley, Flip Korn, Lucia Rossazza, Alexandre Ramé, Sagar Waghmare, Helen Miller, Nathan Byrd, Ashrith Sheshan, Raia Hadsell, Sangnie Bhardwaj, Pawel Janus, Tero Rissa, Dan Horgan, Alvin Abdagic, Lior Belenki, James Allingham, Anima Singh, Theo Guidroz, Srivatsan Srinivasan, Herman Schmit, Kristen Chiafullo, Andre Elisseeff, Nilpa Jha, Prateek Kolhar, Leonard Berrada, Frank Ding, Xiance Si, Shrestha Basu Mallick, Franz Och, Sofia Erell, Eric Ni, Tejasi Latkar, Sherry Yang, Petar Sirkovic, Ziqiang Feng, Robert Leland, Rachel Hornung, Gang Wu, Charles Blundell, Hamidreza Alvari, Po-Sen Huang, Cathy Yip, Sanja Deur, Li Liu, Gabriela Surita, Pablo Duque, Dima Damen, Johnson Jia, Arthur Guez, Markus Mircea, Animesh Sinha, Alberto Magni, Paweł Stradomski, Tal Marian, Vlado Galić, Wenhu Chen, Hisham Husain, Achintya Singhal, Dominik Grewe, François-Xavier Aubet, Shuang Song, Lorenzo Blanco, Leland Rechis, Lewis Ho, Rich Munoz, Kelvin Zheng, Jessica Hamrick, Kevin Mather, Hagai Taitelbaum, Eliza Rutherford, Yun Lei, Kuangyuan Chen, Anand Shukla, Erica Moreira, Eric Doi, Berivan Isik, Nir Shabat, Dominika Rogozińska, Kashyap Kolipaka, Jason Chang, Eugen Vušak, Srinivasan Venkatachary, Shadi Noghabi, Tarun Bharti, Younghoon Jun, Aleksandr Zaks, Simon Green, Jeshwanth Challagundla, William Wong, Muqthar Mohammad, Dean Hirsch, Yong Cheng, Iftekhar Naim, Lev Proleev, Damien Vincent, Aayush Singh, Maxim Krikun, Dilip Krishnan, Zoubin Ghahramani, Aviel Atias, Rajeev Aggarwal, Christo Kirov, Dimitrios Vytiniotis, Christy Koh, Alexandra Chronopoulou, Pawan Dogra, Vlad-Doru Ion, Gladys Tyen, Jason Lee, Felix Weissenberger, Trevor Strohman, Ashwin Balakrishna, Jack Rae, Marko Velic, Raoul de Liedekerke, Oded Elyada, Wentao Yuan, Canoee Liu, Lior Shani, Sergey Kishchenko, Bea Alessio, Yandong Li, Richard Song, Sam Kwei, Orion Jankowski, Aneesh Pappu, Youhei Namiki, Yenai Ma, Nilesh Tripuraneni, Colin Cherry, Marissa Ikonomidis, Yu-Cheng Ling, Colin Ji, Beka Westberg, Auriel Wright, Da Yu, David Parkinson, Swaroop Ramaswamy, Jerome Connor, Soheil Hassas Yeganeh, Snchit Grover, George Kenwright, Lubo Litchev, Chris Apps, Alex Tomala, Felix Halim, Alex Castro-Ros, Zefei Li, Anudhyan Boral, Pauline Sho, Michal Yarom, Eric Malmi, David Klinghoffer, Rebecca Lin, Alan Ansell, Pradeep Kumar S, Shubin Zhao, Siqi Zuo, Adam Santoro, Heng-Tze Cheng, Solomon Demmessie, Yuchi Liu, Nicole Brichtova, Allie Culp, Nathaniel Braun, Dan Graur, Will Ng, Nikhil Mehta, Aaron Phillips, Patrik Sundberg, Varun Godbole, Fangyu Liu, Yash Katariya, David Rim, Mojtaba Seyedhosseini, Sean Ammirati, Jonas Valfridsson, Mahan Malihi, Timothy Knight, Andeep Toor, Thomas Lampe, Abe Ittycheriah, Lewis Chiang, Chak Yeung, Alexandre Fréchette, Jinmeng Rao, Huisheng Wang, Himanshu Srivastava, Richard Zhang, Rocky Rhodes, Ariel Brand, Dean Weesner, Ilya Figotin, Felix Gimeno, Rachana Fellinger, Pierre Marcenac, José Leal, Eyal Marcus, Victor Cotruta, Rodrigo Cabrera, Sheryl Luo, Dan Garrette, Vera Axelrod, Sorin Baltateanu, David Barker, Dongkai Chen, Horia Toma, Ben Ingram, Jason Riesa, Chinmay Kulkarni, Yujing Zhang, Hongbin Liu, Chao Wang, Martin Polacek, Will Wu, Kai Hui, Adrian N Reyes, Yi Su, Megan Barnes, Ishaan Malhi, Anfal Siddiqui, Qixuan Feng, Mihai Damaschin, Daniele Pighin, Andreas Steiner, Samuel Yang, Ramya Sree Boppana, Simeon Ivanov, Arun Kandoor, Aditya Shah, Asier Mujika, Da Huang, Christopher A. Choquette-Choo, Mohak Patel, Tianhe Yu, Toni Creswell, Jerry, Liu, Catarina Barros, Yasaman Razeghi, Aurko Roy, Phil Culliton, Binbin Xiong, Jiaqi Pan, Thomas Strohmann, Tolly Powell, Babi Seal, Doug DeCarlo, Pranav Shyam, Kaan Katircioglu, Xuezhi Wang, Cassidy Hardin, Immanuel Odisho, Josef Broder, Oscar Chang, Arun Nair, Artem Shtefan, Maura O'Brien, Manu Agarwal, Sahitya Potluri, Siddharth Goyal, Amit Jhindal, Saksham Thakur, Yury Stuken, James Lyon, Kristina Toutanova, Fangxiaoyu Feng, Austin Wu, Ben Horn, Alek Wang, Alex Cullum, Gabe Taubman, Disha Shrivastava, Chongyang Shi, Hamish Tomlinson, Roma Patel, Tao Tu, Ada Maksutaj Oflazer, Francesco Pongetti, Mingyao Yang, Adrien Ali Taïga, Vincent Perot, Nuo Wang Pierse, Feng Han, Yoel Drori, Iñaki Iturrate, Ayan Chakrabarti, Legg Yeung, Dave Dopson, Yi-ting Chen, Apoorv Kulshreshtha, Tongfei Guo, Philip Pham, Tal Schuster, Junquan Chen, Alex Polozov, Jinwei Xing, Huanjie Zhou, Praneeth Kacham, Doron Kukliansky, Antoine Miech, Sergey Yaroshenko, Ed Chi, Sholto Douglas, Hongliang Fei, Mathieu Blondel, Preethi Myla, Lior Madmoni, Xing Wu, Daniel Keysers, Kristian Kjems, Isabela Albuquerque, Lijun Yu, Joel D'sa, Michelle Plantan, Vlad Ionescu, Jaume Sanchez Elias, Abhirut Gupta, Manish Reddy Vuyyuru, Fred Alcober, Tong Zhou, Kaiyang Ji, Florian Hartmann, Subha Puttagunta, Hugo Song, Ehsan Amid, Anca Stefanoiu, Andrew Lee, Paul Pucciarelli, Emma Wang, Amit Raul, Slav Petrov, Isaac Tian, Valentin Anklin, Nana Nti, Victor Gomes, Max Schumacher, Grace Vesom, Alex Panagopoulos, Konstantinos Bousmalis, Daniel Andor, Josh Jacob, Yuan Zhang, Bill Rosgen, Matija Kecman, Matthew Tung, Alexandra Belias, Noah Goodman, Paul Covington, Brian Wieder, Nikita Saxena, Elnaz Davoodi, Muhuan Huang, Sharath Maddineni, Vincent Roulet, Folawiyo Campbell-Ajala, Pier Giuseppe Sessa, Xintian, Wu, Guangda Lai, Paul Collins, Alex Haig, Vytenis Sakenas, Xiaowei Xu, Marissa Giustina, Laurent El Shafey, Pichi Charoenpanit, Shefali Garg, Joshua Ainslie, Boone Severson, Montse Gonzalez Arenas, Shreya Pathak, Sujee Rajayogam, Jie Feng, Michiel Bakker, Sheng Li, Nevan Wichers, Jamie Rogers, Xinyang Geng, Yeqing Li, Rolf Jagerman, Chao Jia, Nadav Olmert, David Sharon, Matthew Mauger, Sandeep Mariserla, Hongxu Ma, Megha Mohabey, Kyuyeun Kim, Alek Andreev, Scott Pollom, Juliette Love, Vihan Jain, Priyanka Agrawal, Yannick Schroecker, Alisa Fortin, Manfred Warmuth, Ji Liu, Andrew Leach, Irina Blok, Ganesh Poomal Girirajan, Roee Aharoni, Benigno Uria, Andrei Sozanschi, Dan Goldberg, Lucian Ionita, Marco Tulio Ribeiro, Martin Zlocha, Vighnesh Birodkar, Sami Lachgar, Liangzhe Yuan, Himadri Choudhury, Matt Ginsberg, Fei Zheng, Gregory Dibb, Emily Graves, Swachhand Lokhande, Gabriel Rasskin, George-Cristian Muraru, Corbin Quick, Sandeep Tata, Pierre Sermanet, Aditya Chawla, Itay Karo, Yan Wang, Susan Zhang, Orgad Keller, Anca Dragan, Guolong Su, Ian Chou, Xi Liu, Yiqing Tao, Shruthi Prabhakara, Marc Wilson, Ruibo Liu, Shibo Wang, Georgie Evans, David Du, Alfonso Castaño, Gautam Prasad, Mona El Mahdy, Sebastian Gerlach, Machel Reid, Jarrod Kahn, Amir Zait, Thanumalayan Sankaranarayana Pillai, Thatcher Ulrich, Guanyu Wang, Jan Wassenberg, Efrat Farkash, Kiran Yalasangi, Congchao Wang, Maria Bauza, Simon Bucher, Ting Liu, Jun Yan, Gary Leung, Vikas Sindhwani, Parker Barnes, Avi Singh, Ivan Jurin, Jichuan Chang, Niket Kumar Bhumihar, Sivan Eiger, Gui Citovsky, Ben Withbroe, Zhang Li, Siyang Xue, Niccolò Dal Santo, Georgi Stoyanov, Yves Raimond, Steven Zheng, Yilin Gao, Vít Listík, Sławek Kwasiborski, Rachel Saputro, Adnan Ozturel, Ganesh Mallya, Kushal Majmundar, Ross West, Paul Caron, Jinliang Wei, Lluis Castrejon, Sharad Vikram, Deepak Ramachandran, Nikhil Dhawan, Jiho Park, Sara Smoot, George van den Driessche, Yochai Blau, Chase Malik, Wei Liang, Roy Hirsch, Cicero Nogueira dos Santos, Eugene Weinstein, Aäron van den Oord, Sid Lall, Nicholas FitzGerald, Zixuan Jiang, Xuan Yang, Dale Webster, Ali Elqursh, Aedan Pope, Georges Rotival, David Raposo, Wanzheng Zhu, Jeff Dean, Sami Alabed, Dustin Tran, Arushi Gupta, Zach Gleicher, Jessica Austin, Edouard Rosseel, Megh Umekar, Dipanjan Das, Yinghao Sun, Kai Chen, Karolis Misiunas, Xiang Zhou, Yixian Di, Alyssa Loo, Josh Newlan, Bo Li, Vinay Ramasesh, Ying Xu, Alex Chen, Sudeep Gandhe, Radu Soricut, Nikita Gupta, Shuguang Hu, Seliem El-Sayed, Xavier Garcia, Idan Brusilovsky, Pu-Chin Chen, Andrew Bolt, Lu Huang, Alex Gurney, Zhiying Zhang, Alexander Pritzel, Jarek Wilkiewicz, Bryan Seybold, Bhargav Kanagal Shamanna, Felix Fischer, Josef Dean, Karan Gill, Ross Mcilroy, Abhishek Bhowmick, Jeremy Selier, Antoine Yang, Derek Cheng, Vladimir Magay, Jie Tan, Dhriti Varma, Christian Walder, Tomas Kocisky, Ryo Nakashima, Paul Natsev, Mike Kwong, Ionel Gog, Chiyuan Zhang, Sander Dieleman, Thomas Jimma, Andrey Ryabtsev, Siddhartha Brahma, David Steiner, Dayou Du, Ante Žužul, Mislav Žanić, Mukund Raghavachari, Willi Gierke, Zeyu Zheng, Dessie Petrova, Yann Dauphin, Yuchuan Liu, Ido Kessler, Steven Hand, Chris Duvarney, Seokhwan Kim, Hyo Lee, Léonard Hussenot, Jeffrey Hui, Josh Smith, Deepali Jain, Jiawei Xia, Gaurav Singh Tomar, Keyvan Amiri, Du Phan, Fabian Fuchs, Tobias Weyand, Nenad Tomasev, Alexandra Cordell, Xin Liu, Jonathan Mallinson, Pankaj Joshi, Andy Crawford, Arun Suggala, Steve Chien, Nick Fernando, Mariella Sanchez-Vargas, Duncan Williams, Phil Crone, Xiyang Luo, Igor Karpov, Jyn Shan, Terry Thurk, Robin Strudel, Paul Voigtlaender, Piyush Patil, Tim Dozat, Ali Khodaei, Sahil Singla, Piotr Ambroszczyk, Qiyin Wu, Yifan Chang, Brian Roark, Chaitra Hegde, Tianli Ding, Angelos Filos, Zhongru Wu, André Susano Pinto, Shuang Liu, Saarthak Khanna, Aditya Pandey, Siobhan Mcloughlin, Qiujia Li, Sam Haves, Allan Zhou, Elena Buchatskaya, Isabel Leal, Peter de Boursac, Nami Akazawa, Nina Anderson, Terry Chen, Krishna Somandepalli, Chen Liang, Sheela Goenka, Stephanie Winkler, Alexander Grushetsky, Yifan Ding, Jamie Smith, Fan Ye, Jordi Pont-Tuset, Eric Li, Ruichao Li, Tomer Golany, Dawid Wegner, Tao Jiang, Omer Barak, Yuan Shangguan, Eszter Vértes, Renee Wong, Jörg Bornschein, Alex Tudor, Michele Bevilacqua, Tom Schaul, Ankit Singh Rawat, Yang Zhao, Kyriakos Axiotis, Lei Meng, Cory McLean, Jonathan Lai, Jennifer Beattie, Nate Kushman, Yaxin Liu, Blair Kutzman, Fiona Lang, Jingchen Ye, Praneeth Netrapalli, Pushkar Mishra, Myriam Khan, Megha Goel, Rob Willoughby, David Tian, Honglei Zhuang, JD Chen, Zak Tsai, Tasos Kementsietsidis, Arjun Khare, James Keeling, Keyang Xu, Nathan Waters, Florent Altché, Ashok Popat, Bhavishya Mittal, David Saxton, Dalia El Badawy, Michael Mathieu, Zheng Zheng, Hao Zhou, Nishant Ranka, Richard Shin, Qingnan Duan, Tim Salimans, Ioana Mihailescu, Uri Shaham, Ming-Wei Chang, Yannis Assael, Nishanth Dikkala, Martin Izzard, Vincent Cohen-Addad, Cat Graves, Vlad Feinberg, Grace Chung, DJ Strouse, Danny Karmon, Sahand Sharifzadeh, Zoe Ashwood, Khiem Pham, Jon Blanton, Alex Vasiloff, Jarred Barber, Mark Geller, Aurick Zhou, Fedir Zubach, Tzu-Kuo Huang, Lei Zhang, Himanshu Gupta, Matt Young, Julia Proskurnia, Ronny Votel, Valentin Gabeur, Gabriel Barcik, Aditya Tripathi, Hongkun Yu, Geng Yan, Beer Changpinyo, Filip Pavetić, Amy Coyle, Yasuhisa Fujii, Jorge Gonzalez Mendez, Tianhao Zhou, Harish Rajamani, Blake Hechtman, Eddie Cao, Da-Cheng Juan, Yi-Xuan Tan, Valentin Dalibard, Yilun Du, Natalie Clay, Kaisheng Yao, Wenhao Jia, Dimple Vijaykumar, Yuxiang Zhou, Xinyi Bai, Wei-Chih Hung, Steven Pecht, Georgi Todorov, Nikhil Khadke, Pramod Gupta, Preethi Lahoti, Arnaud Autef, Karthik Duddu, James Lee-Thorp, Alexander Bykovsky, Tautvydas Misiunas, Sebastian Flennerhag, Santhosh Thangaraj, Jed McGiffin, Zack Nado, Markus Kunesch, Andreas Noever, Amir Hertz, Marco Liang, Victor Stone, Evan Palmer, Samira Daruki, Arijit Pramanik, Siim Põder, Austin Kyker, Mina Khan, Evgeny Sluzhaev, Marvin Ritter, Avraham Ruderman, Wenlei Zhou, Chirag Nagpal, Kiran Vodrahalli, George Necula, Paul Barham, Ellie Pavlick, Jay Hartford, Izhak Shafran, Long Zhao, Maciej Mikuła, Tom Eccles, Hidetoshi Shimokawa, Kanav Garg, Luke Vilnis, Hanwen Chen, Ilia Shumailov, Kuang-Huei Lee, Abdelrahman Abdelhamed, Meiyan Xie, Vered Cohen, Ester Hlavnova, Dan Malkin, Chawin Sitawarin, James Lottes, Pauline Coquinot, Tianli Yu, Sandeep Kumar, Jingwei Zhang, Aroma Mahendru, Zafarali Ahmed, James Martens, Tao Chen, Aviel Boag, Daiyi Peng, Coline Devin, Arseniy Klimovskiy, Mary Phuong, Danny Vainstein, Jin Xie, Bhuvana Ramabhadran, Nathan Howard, Xinxin Yu, Gitartha Goswami, Jingyu Cui, Sam Shleifer, Mario Pinto, Chih-Kuan Yeh, Ming-Hsuan Yang, Sara Javanmardi, Dan Ethier, Chace Lee, Jordi Orbay, Suyog Kotecha, Carla Bromberg, Pete Shaw, James Thornton, Adi Gerzi Rosenthal, Shane Gu, Matt Thomas, Ian Gemp, Aditya Ayyar, Asahi Ushio, Aarush Selvan, Joel Wee, Chenxi Liu, Maryam Majzoubi, Weiren Yu, Jake Abernethy, Tyler Liechty, Renke Pan, Hoang Nguyen, Qiong, Hu, Sarah Perrin, Abhinav Arora, Emily Pitler, Weiyi Wang, Kaushik Shivakumar, Flavien Prost, Ben Limonchik, Jing Wang, Yi Gao, Timothee Cour, Shyamal Buch, Huan Gui, Maria Ivanova, Philipp Neubeck, Kelvin Chan, Lucy Kim, Huizhong Chen, Naman Goyal, Da-Woon Chung, Lu Liu, Yao Su, Anastasia Petrushkina, Jiajun Shen, Armand Joulin, Yuanzhong Xu, Stein Xudong Lin, Yana Kulizhskaya, Ciprian Chelba, Shobha Vasudevan, Eli Collins, Vasilisa Bashlovkina, Tony Lu, Doug Fritz, Jongbin Park, Yanqi Zhou, Chen Su, Richard Tanburn, Mikhail Sushkov, Mitchelle Rasquinha, Jinning Li, Jennifer Prendki, Yiming Li, Pallavi LV, Shriya Sharma, Hen Fitoussi, Hui Huang, Andrew Dai, Phuong Dao, Mike Burrows, Henry Prior, Danfeng Qin, Golan Pundak, Lars Lowe Sjoesund, Art Khurshudov, Zhenkai Zhu, Albert Webson, Elizabeth Kemp, Tat Tan, Saurabh Agrawal, Susie Sargsyan, Liqun Cheng, Jim Stephan, Tom Kwiatkowski, David Reid, Arunkumar Byravan, Assaf Hurwitz Michaely, Nicolas Heess, Luowei Zhou, Sonam Goenka, Viral Carpenter, Anselm Levskaya, Bo Wang, Reed Roberts, Rémi Leblond, Sharat Chikkerur, Stav Ginzburg, Max Chang, Robert Riachi, Chuqiao, Xu, Zalán Borsos, Michael Pliskin, Julia Pawar, Morgane Lustman, Hannah Kirkwood, Ankit Anand, Aditi Chaudhary, Norbert Kalb, Kieran Milan, Sean Augenstein, Anna Goldie, Laurel Prince, Karthik Raman, Yanhua Sun, Vivian Xia, Aaron Cohen, Zhouyuan Huo, Josh Camp, Seher Ellis, Lukas Zilka, David Vilar Torres, Lisa Patel, Sho Arora, Betty Chan, Jonas Adler, Kareem Ayoub, Jacky Liang, Fayaz Jamil, Jiepu Jiang, Simon Baumgartner, Haitian Sun, Yael Karov, Yaroslav Akulov, Hui Zheng, Irene Cai, Claudio Fantacci, James Rubin, Alex Rav Acha, Mengchao Wang, Nina D'Souza, Rohit Sathyanarayana, Shengyang Dai, Simon Rowe, Andrey Simanovsky, Omer Goldman, Yuheng Kuang, Xiaoyue Pan, Andrew Rosenberg, Tania Rojas-Esponda, Praneet Dutta, Amy Zeng, Irina Jurenka, Greg Farquhar, Yamini Bansal, Shariq Iqbal, Becca Roelofs, Ga-Young Joung, Parker Beak, Changwan Ryu, Ryan Poplin, Yan Wu, Jean-Baptiste Alayrac, Senaka Buthpitiya, Olaf Ronneberger, Caleb Habtegebriel, Wei Li, Paul Cavallaro, Aurora Wei, Guy Bensky, Timo Denk, Harish Ganapathy, Jeff Stanway, Pratik Joshi, Francesco Bertolini, Jessica Lo, Olivia Ma, Zachary Charles, Geta Sampemane, Himanshu Sahni, Xu Chen, Harry Askham, David Gaddy, Peter Young, Jiewen Tan, Matan Eyal, Arthur Bražinskas, Li Zhong, Zhichun Wu, Mark Epstein, Kai Bailey, Andrew Hard, Kamyu Lee, Sasha Goldshtein, Alex Ruiz, Mohammed Badawi, Matthias Lochbrunner, JK Kearns, Ashley Brown, Fabio Pardo, Theophane Weber, Haichuan Yang, Pan-Pan Jiang, Berkin Akin, Zhao Fu, Marcus Wainwright, Chi Zou, Meenu Gaba, Pierre-Antoine Manzagol, Wendy Kan, Yang Song, Karina Zainullina, Rui Lin, Jeongwoo Ko, Salil Deshmukh, Apoorv Jindal, James Svensson, Divya Tyam, Heri Zhao, Christine Kaeser-Chen, Scott Baird, Pooya Moradi, Jamie Hall, Qiuchen Guo, Vincent Tsang, Bowen Liang, Fernando Pereira, Suhas Ganesh, Ivan Korotkov, Jakub Adamek, Sridhar Thiagarajan, Vinh Tran, Charles Chen, Chris Tar, Sanil Jain, Ishita Dasgupta, Taylan Bilal, David Reitter, Kai Zhao, Giulia Vezzani, Yasmin Gehman, Pulkit Mehta, Lauren Beltrone, Xerxes Dotiwalla, Sergio Guadarrama, Zaheer Abbas, Stefani Karp, Petko Georgiev, Chun-Sung Ferng, Marc Brockschmidt, Liqian Peng, Christoph Hirnschall, Vikas Verma, Yingying Bi, Ying Xiao, Avigail Dabush, Kelvin Xu, Phil Wallis, Randall Parker, Qifei Wang, Yang Xu, Ilkin Safarli, Dinesh Tewari, Yin Zhang, Seungyeon Kim, Andrea Gesmundo, Mackenzie Thomas, Sergey Levi, Ahmed Chowdhury, Kanishka Rao, Peter Garst, Sam Conway-Rahman, Helen Ran, Kay McKinney, Zhisheng Xiao, Wenhao Yu, Rohan Agrawal, Axel Stjerngren, Catalin Ionescu, Jingjing Chen, Vivek Sharma, Justin Chiu, Fei Liu, Ken Franko, Clayton Sanford, Xingyu Cai, Paul Michel, Sanjay Ganapathy, Jane Labanowski, Zachary Garrett, Ben Vargas, Sean Sun, Bryan Gale, Thomas Buschmann, Guillaume Desjardins, Nimesh Ghelani, Palak Jain, Mudit Verma, Chulayuth Asawaroengchai, Julian Eisenschlos, Jitendra Harlalka, Hideto Kazawa, Don Metzler, Joshua Howland, Ying Jian, Jake Ades, Viral Shah, Tynan Gangwani, Seungji Lee, Roman Ring, Steven M. Hernandez, Dean Reich, Amer Sinha, Ashutosh Sathe, Joe Kovac, Ashleah Gill, Ajay Kannan, Andrea D'olimpio, Martin Sevenich, Jay Whang, Been Kim, Khe Chai Sim, Jilin Chen, Jiageng Zhang, Shuba Lall, Yossi Matias, Bill Jia, Abe Friesen, Sara Nasso, Ashish Thapliyal, Bryan Perozzi, Ting Yu, Anna Shekhawat, Safeen Huda, Peter Grabowski, Eric Wang, Ashwin Sreevatsa, Hilal Dib, Mehadi Hassen, Parker Schuh, Vedrana Milutinovic, Chris Welty, Michael Quinn, Ali Shah, Bangju Wang, Gabe Barth-Maron, Justin Frye, Natalie Axelsson, Tao Zhu, Yukun Ma, Irene Giannoumis, Hanie Sedghi, Chang Ye, Yi Luan, Kevin Aydin, Bilva Chandra, Vivek Sampathkumar, Ronny Huang, Victor Lavrenko, Ahmed Eleryan, Zhi Hong, Steven Hansen, Sara Mc Carthy, Bidisha Samanta, Domagoj Ćevid, Xin Wang, Fangtao Li, Michael Voznesensky, Matt Hoffman, Andreas Terzis, Vikash Sehwag, Gil Fidel, Luheng He, Mu Cai, Yanzhang He, Alex Feng, Martin Nikoltchev, Samrat Phatale, Jason Chase, Rory Lawton, Ming Zhang, Tom Ouyang, Manuel Tragut, Mehdi Hafezi Manshadi, Arjun Narayanan, Jiaming Shen, Xu Gao, Tolga Bolukbasi, Nick Roy, Xin Li, Daniel Golovin, Liviu Panait, Zhen Qin, Guangxing Han, Thomas Anthony, Sneha Kudugunta, Viorica Patraucean, Aniket Ray, Xinyun Chen, Xiaochen Yang, Tanuj Bhatia, Pranav Talluri, Alex Morris, Andrija Ražnatović, Bethanie Brownfield, James An, Sheng Peng, Patrick Kane, Ce Zheng, Nico Duduta, Joshua Kessinger, James Noraky, Siqi Liu, Keran Rong, Petar Veličković, Keith Rush, Alex Goldin, Fanny Wei, Shiva Mohan Reddy Garlapati, Caroline Pantofaru, Okwan Kwon, Jianmo Ni, Eric Noland, Julia Di Trapani, Françoise Beaufays, Abhijit Guha Roy, Yinlam Chow, Aybuke Turker, Geoffrey Cideron, Lantao Mei, Jon Clark, Qingyun Dou, Matko Bošnjak, Ralph Leith, Yuqing Du, Amir Yazdanbakhsh, Milad Nasr, Chester Kwak, Suraj Satishkumar Sheth, Alex Kaskasoli, Ankesh Anand, Balaji Lakshminarayanan, Sammy Jerome, David Bieber, Chun-Te Chu, Alexandre Senges, Tianxiao Shen, Mukund Sridhar, Ndaba Ndebele, Benjamin Beyret, Shakir Mohamed, Mia Chen, Markus Freitag, Jiaxian Guo, Luyang Liu, Paul Roit, Heng Chen, Shen Yan, Tom Stone, JD Co-Reyes, Jeremy Cole, Salvatore Scellato, Shekoofeh Azizi, Hadi Hashemi, Alicia Jin, Anand Iyer, Marcella Valentine, András György, Arun Ahuja, Daniel Hernandez Diaz, Chen-Yu Lee, Nathan Clement, Weize Kong, Drew Garmon, Ishaan Watts, Kush Bhatia, Khyatti Gupta, Matt Miecnikowski, Hugo Vallet, Ankur Taly, Edward Loper, Saket Joshi, James Atwood, Jo Chick, Mark Collier, Fotis Iliopoulos, Ryan Trostle, Beliz Gunel, Ramiro Leal-Cavazos, Arnar Mar Hrafnkelsson, Michael Guzman, Xiaoen Ju, Andy Forbes, Jesse Emond, Kushal Chauhan, Ben Caine, Li Xiao, Wenjun Zeng, Alexandre Moufarek, Daniel Murphy, Maya Meng, Nitish Gupta, Felix Riedel, Anil Das, Elijah Lawal, Shashi Narayan, Tiberiu Sosea, James Swirhun, Linda Friso, Behnam Neyshabur, Jing Lu, Sertan Girgin, Michael Wunder, Edouard Yvinec, Aroonalok Pyne, Victor Carbune, Shruti Rijhwani, Yang Guo, Tulsee Doshi, Anton Briukhov, Max Bain, Ayal Hitron, Xuanhui Wang, Ashish Gupta, Ke Chen, Cosmo Du, Weiyang Zhang, Dhruv Shah, Arjun Akula, Max Dylla, Ashyana Kachra, Weicheng Kuo, Tingting Zou, Lily Wang, Luyao Xu, Jifan Zhu, Justin Snyder, Sachit Menon, Orhan Firat, Igor Mordatch, Yuan Yuan, Natalia Ponomareva, Rory Blevins, Lawrence Moore, Weijun Wang, Phil Chen, Martin Scholz, Artur Dwornik, Jason Lin, Sicheng Li, Diego Antognini, Te I, Xiaodan Song, Matt Miller, Uday Kalra, Adam Raveret, Oscar Akerlund, Felix Wu, Andrew Nystrom, Namrata Godbole, Tianqi Liu, Hannah DeBalsi, Jewel Zhao, Buhuang Liu, Avi Caciularu, Lauren Lax, Urvashi Khandelwal, Victoria Langston, Eric Bailey, Silvio Lattanzi, Yufei Wang, Neel Kovelamudi, Sneha Mondal, Guru Guruganesh, Nan Hua, Ofir Roval, Paweł Wesołowski, Rishikesh Ingale, Jonathan Halcrow, Tim Sohn, Christof Angermueller, Bahram Raad, Eli Stickgold, Eva Lu, Alec Kosik, Jing Xie, Timothy Lillicrap, Austin Huang, Lydia Lihui Zhang, Dominik Paulus, Clement Farabet, Alex Wertheim, Bing Wang, Rishabh Joshi, Chu-ling Ko, Yonghui Wu, Shubham Agrawal, Lily Lin, XiangHai Sheng, Peter Sung, Tyler Breland-King, Christina Butterfield, Swapnil Gawde, Sumeet Singh, Qiao Zhang, Raj Apte, Shilpa Shetty, Adrian Hutter, Tao Li, Elizabeth Salesky, Federico Lebron, Jonni Kanerva, Michela Paganini, Arthur Nguyen, Rohith Vallu, Jan-Thorsten Peter, Sarmishta Velury, David Kao, Jay Hoover, Anna Bortsova, Colton Bishop, Shoshana Jakobovits, Alessandro Agostini, Alekh Agarwal, Chang Liu, Charles Kwong, Sasan Tavakkol, Ioana Bica, Alex Greve, Anirudh GP, Jake Marcus, Le Hou, Tom Duerig, Rivka Moroshko, Dave Lacey, Andy Davis, Julien Amelot, Guohui Wang, Frank Kim, Theofilos Strinopoulos, Hui Wan, Charline Le Lan, Shankar Krishnan, Haotian Tang, Peter Humphreys, Junwen Bai, Idan Heimlich Shtacher, Diego Machado, Chenxi Pang, Ken Burke, Dangyi Liu, Renga Aravamudhan, Yue Song, Ed Hirst, Abhimanyu Singh, Brendan Jou, Liang Bai, Francesco Piccinno, Chuyuan Kelly Fu, Robin Alazard, Barak Meiri, Daniel Winter, Charlie Chen, Mingda Zhang, Jens Heitkaemper, John Lambert, Jinhyuk Lee, Alexander Frömmgen, Sergey Rogulenko, Pranav Nair, Paul Niemczyk, Anton Bulyenov, Bibo Xu, Hadar Shemtov, Morteza Zadimoghaddam, Serge Toropov, Mateo Wirth, Hanjun Dai, Sreenivas Gollapudi, Daniel Zheng, Alex Kurakin, Chansoo Lee, Kalesha Bullard, Nicolas Serrano, Ivana Balazevic, Yang Li, Johan Schalkwyk, Mark Murphy, Mingyang Zhang, Kevin Sequeira, Romina Datta, Nishant Agrawal, Charles Sutton, Nithya Attaluri, Mencher Chiang, Wael Farhan, Gregory Thornton, Kate Lin, Travis Choma, Hung Nguyen, Kingshuk Dasgupta, Dirk Robinson, Iulia Comşa, Michael Riley, Arjun Pillai, Basil Mustafa, Ben Golan, Amir Zandieh, Jean-Baptiste Lespiau, Billy Porter, David Ross, Sujeevan Rajayogam, Mohit Agarwal, Subhashini Venugopalan, Bobak Shahriari, Qiqi Yan, Hao Xu, Taylor Tobin, Pavel Dubov, Hongzhi Shi, Adrià Recasens, Anton Kovsharov, Sebastian Borgeaud, Lucio Dery, Shanthal Vasanth, Elena Gribovskaya, Linhai Qiu, Mahdis Mahdieh, Wojtek Skut, Elizabeth Nielsen, CJ Zheng, Adams Yu, Carrie Grimes Bostock, Shaleen Gupta, Aaron Archer, Chris Rawles, Elinor Davies, Alexey Svyatkovskiy, Tomy Tsai, Yoni Halpern, Christian Reisswig, Bartek Wydrowski, Bo Chang, Joan Puigcerver, Mor Hazan Taege, Jian Li, Eva Schnider, Xinjian Li, Dragos Dena, Yunhan Xu, Umesh Telang, Tianze Shi, Heiga Zen, Kyle Kastner, Yeongil Ko, Neesha Subramaniam, Aviral Kumar, Pete Blois, Zhuyun Dai, John Wieting, Yifeng Lu, Yoel Zeldes, Tian Xie, Anja Hauth, Alexandru Ţifrea, Yuqi Li, Sam El-Husseini, Dan Abolafia, Howard Zhou, Wen Ding, Sahra Ghalebikesabi, Carlos Guía, Andrii Maksai, Ágoston Weisz, Sercan Arik, Nick Sukhanov, Aga Świetlik, Xuhui Jia, Luo Yu, Weiyue Wang, Mark Brand, Dawn Bloxwich, Sean Kirmani, Zhe Chen, Alec Go, Pablo Sprechmann, Nithish Kannen, Alen Carin, Paramjit Sandhu, Isabel Edkins, Leslie Nooteboom, Jai Gupta, Loren Maggiore, Javad Azizi, Yael Pritch, Pengcheng Yin, Mansi Gupta, Danny Tarlow, Duncan Smith, Desi Ivanov, Mohammad Babaeizadeh, Ankita Goel, Satish Kambala, Grace Chu, Matej Kastelic, Michelle Liu, Hagen Soltau, Austin Stone, Shivani Agrawal, Min Kim, Kedar Soparkar, Srinivas Tadepalli, Oskar Bunyan, Rachel Soh, Arvind Kannan, DY Kim, Blake JianHang Chen, Afief Halumi, Sudeshna Roy, Yulong Wang, Olcan Sercinoglu, Gena Gibson, Sijal Bhatnagar, Motoki Sano, Daniel von Dincklage, Qingchun Ren, Blagoj Mitrevski, Mirek Olšák, Jennifer She, Carl Doersch, Jilei, Wang, Bingyuan Liu, Qijun Tan, Tamar Yakar, Tris Warkentin, Alex Ramirez, Carl Lebsack, Josh Dillon, Rajiv Mathews, Tom Cobley, Zelin Wu, Zhuoyuan Chen, Jon Simon, Swaroop Nath, Tara Sainath, Alexei Bendebury, Ryan Julian, Bharath Mankalale, Daria Ćurko, Paulo Zacchello, Adam R. Brown, Kiranbir Sodhia, Heidi Howard, Sergi Caelles, Abhinav Gupta, Gareth Evans, Anna Bulanova, Lesley Katzen, Roman Goldenberg, Anton Tsitsulin, Joe Stanton, Benoit Schillings, Vitaly Kovalev, Corey Fry, Rushin Shah, Kuo Lin, Shyam Upadhyay, Cheng Li, Soroush Radpour, Marcello Maggioni, Jing Xiong, Lukas Haas, Jenny Brennan, Aishwarya Kamath, Nikolay Savinov, Arsha Nagrani, Trevor Yacovone, Ryan Kappedal, Kostas Andriopoulos, Li Lao, YaGuang Li, Grigory Rozhdestvenskiy, Kazuma Hashimoto, Andrew Audibert, Sophia Austin, Daniel Rodriguez, Anian Ruoss, Garrett Honke, Deep Karkhanis, Xi Xiong, Qing Wei, James Huang, Zhaoqi Leng, Vittal Premachandran, Stan Bileschi, Georgios Evangelopoulos, Thomas Mensink, Jay Pavagadhi, Denis Teplyashin, Paul Chang, Linting Xue, Garrett Tanzer, Sally Goldman, Kaushal Patel, Shixin Li, Jeremy Wiesner, Ivy Zheng, Ian Stewart-Binks, Jie Han, Zhi Li, Liangchen Luo, Karel Lenc, Mario Lučić, Fuzhao Xue, Ryan Mullins, Alexey Guseynov, Chung-Ching Chang, Isaac Galatzer-Levy, Adam Zhang, Garrett Bingham, Grace Hu, Ale Hartman, Yue Ma, Jordan Griffith, Alex Irpan, Carey Radebaugh, Summer Yue, Lijie Fan, Victor Ungureanu, Christina Sorokin, Hannah Teufel, Peiran Li, Rohan Anil, Dimitris Paparas, Todd Wang, Chu-Cheng Lin, Hui Peng, Megan Shum, Goran Petrovic, Demetra Brady, Richard Nguyen, Klaus Macherey, Zhihao Li, Harman Singh, Madhavi Yenugula, Mariko Iinuma, Xinyi Chen, Kavya Kopparapu, Alexey Stern, Shachi Dave, Chandu Thekkath, Florence Perot, Anurag Kumar, Fangda Li, Yang Xiao, Matthew Bilotti, Mohammad Hossein Bateni, Isaac Noble, Lisa Lee, Amelio Vázquez-Reina, Julian Salazar, Xiaomeng Yang, Boyu Wang, Ela Gruzewska, Anand Rao, Sindhu Raghuram, Zheng Xu, Eyal Ben-David, Jieru Mei, Sid Dalmia, Zhaoyi Zhang, Yuchen Liu, Gagan Bansal, Helena Pankov, Steven Schwarcz, Andrea Burns, Christine Chan, Sumit Sanghai, Ricky Liang, Ethan Liang, Antoine He, Amy Stuart, Arun Narayanan, Yukun Zhu, Christian Frank, Bahar Fatemi, Amit Sabne, Oran Lang, Indro Bhattacharya, Shane Settle, Maria Wang, Brendan McMahan, Andrea Tacchetti, Livio Baldini Soares, Majid Hadian, Serkan Cabi, Timothy Chung, Nikita Putikhin, Gang Li, Jeremy Chen, Austin Tarango, Henryk Michalewski, Mehran Kazemi, Hussain Masoom, Hila Sheftel, Rakesh Shivanna, Archita Vadali, Ramona Comanescu, Doug Reid, Joss Moore, Arvind Neelakantan, Michaël Sander, Jonathan Herzig, Aviv Rosenberg, Mostafa Dehghani, JD Choi, Michael Fink, Reid Hayes, Eric Ge, Shitao Weng, Chia-Hua Ho, John Karro, Kalpesh Krishna, Lam Nguyen Thiet, Amy Skerry-Ryan, Daniel Eppens, Marco Andreetto, Navin Sarma, Silvano Bonacina, Burcu Karagol Ayan, Megha Nawhal, Zhihao Shan, Mike Dusenberry, Shantanu Thakoor, Sagar Gubbi, Duc Dung Nguyen, Reut Tsarfaty, Samuel Albanie, Jovana Mitrović, Meet Gandhi, Bo-Juen Chen, Alessandro Epasto, Georgi Stephanov, Ye Jin, Samuel Gehman, Aida Amini, Jack Weber, Feryal Behbahani, Shawn Xu, Miltos Allamanis, Xi Chen, Myle Ott, Claire Sha, Michal Jastrzebski, Hang Qi, David Greene, Xinyi Wu, Abodunrinwa Toki, Daniel Vlasic, Jane Shapiro, Ragha Kotikalapudi, Zhe Shen, Takaaki Saeki, Sirui Xie, Albin Cassirer, Shikhar Bharadwaj, Tatsuya Kiyono, Srinadh Bhojanapalli, Elan Rosenfeld, Sam Ritter, Jieming Mao, João Gabriel Oliveira, Zoltan Egyed, Bernd Bandemer, Emilio Parisotto, Keisuke Kinoshita, Juliette Pluto, Petros Maniatis, Steve Li, Yaohui Guo, Golnaz Ghiasi, Jean Tarbouriech, Srimon Chatterjee, Julie Jin, Katrina, Xu, Jennimaria Palomaki, Séb Arnold, Madhavi Sewak, Federico Piccinini, Mohit Sharma, Ben Albrecht, Sean Purser-haskell, Ashwin Vaswani, Chongyan Chen, Matheus Wisniewski, Qin Cao, John Aslanides, Nguyet Minh Phu, Maximilian Sieb, Lauren Agubuzu, Anne Zheng, Daniel Sohn, Marco Selvi, Anders Andreassen, Krishan Subudhi, Prem Eruvbetine, Oliver Woodman, Tomas Mery, Sebastian Krause, Xiaoqi Ren, Xiao Ma, Jincheng Luo, Dawn Chen, Wei Fan, Henry Griffiths, Christian Schuler, Alice Li, Shujian Zhang, Jean-Michel Sarr, Shixin Luo, Riccardo Patana, Matthew Watson, Dani Naboulsi, Michael Collins, Sailesh Sidhwani, Emiel Hoogeboom, Sharon Silver, Emily Caveness, Xiaokai Zhao, Mikel Rodriguez, Maxine Deines, Libin Bai, Patrick Griffin, Marco Tagliasacchi, Emily Xue, Spandana Raj Babbula, Bo Pang, Nan Ding, Gloria Shen, Elijah Peake, Remi Crocker, Shubha Srinivas Raghvendra, Danny Swisher, Woohyun Han, Richa Singh, Ling Wu, Vladimir Pchelin, Tsendsuren Munkhdalai, Dana Alon, Geoff Bacon, Efren Robles, Jannis Bulian, Melvin Johnson, George Powell, Felipe Tiengo Ferreira, Yaoyiran Li, Frederik Benzing, Mihajlo Velimirović, Hubert Soyer, William Kong, Tony, Nguyên, Zhen Yang, Jeremiah Liu, Joost van Amersfoort, Daniel Gillick, Baochen Sun, Nathalie Rauschmayr, Katie Zhang, Serena Zhan, Tao Zhou, Alexey Frolov, Chengrun Yang, Denis Vnukov, Louis Rouillard, Hongji Li, Amol Mandhane, Nova Fallen, Rajesh Venkataraman, Clara Huiyi Hu, Jennifer Brennan, Jenny Lee, Jerry Chang, Martin Sundermeyer, Zhufeng Pan, Rosemary Ke, Simon Tong, Alex Fabrikant, William Bono, Jindong Gu, Ryan Foley, Yiran Mao, Manolis Delakis, Dhruva Bhaswar, Roy Frostig, Nick Li, Avital Zipori, Cath Hope, Olga Kozlova, Swaroop Mishra, Josip Djolonga, Craig Schiff, Majd Al Merey, Eleftheria Briakou, Peter Morgan, Andy Wan, Avinatan Hassidim, RJ Skerry-Ryan, Kuntal Sengupta, Mary Jasarevic, Praveen Kallakuri, Paige Kunkle, Hannah Brennan, Tom Lieber, Hassan Mansoor, Julian Walker, Bing Zhang, Annie Xie, Goran Žužić, Adaeze Chukwuka, Alex Druinsky, Donghyun Cho, Rui Yao, Ferjad Naeem, Shiraz Butt, Eunyoung Kim, Zhipeng Jia, Mandy Jordan, Adam Lelkes, Mark Kurzeja, Sophie Wang, James Zhao, Andrew Over, Abhishek Chakladar, Marcel Prasetya, Neha Jha, Sriram Ganapathy, Yale Cong, Prakash Shroff, Carl Saroufim, Sobhan Miryoosefi, Mohamed Hammad, Tajwar Nasir, Weijuan Xi, Yang Gao, Young Maeng, Ben Hora, Chin-Yi Cheng, Parisa Haghani, Yoad Lewenberg, Caden Lu, Martin Matysiak, Naina Raisinghani, Huiyu Wang, Lexi Baugher, Rahul Sukthankar, Minh Giang, John Schultz, Noah Fiedel, Minmin Chen, Cheng-Chun Lee, Tapomay Dey, Hao Zheng, Shachi Paul, Celine Smith, Andy Ly, Yicheng Wang, Rishabh Bansal, Bartek Perz, Susanna Ricco, Stasha Blank, Vaishakh Keshava, Deepak Sharma, Marvin Chow, Kunal Lad, Komal Jalan, Simon Osindero, Craig Swanson, Jacob Scott, Anastasija Ilić, Xiaowei Li, Siddhartha Reddy Jonnalagadda, Afzal Shama Soudagar, Yan Xiong, Bat-Orgil Batsaikhan, Daniel Jarrett, Naveen Kumar, Maulik Shah, Matt Lawlor, Austin Waters, Mark Graham, Rhys May, Sabela Ramos, Sandra Lefdal, Zeynep Cankara, Nacho Cano, Brendan O'Donoghue, Jed Borovik, Frederick Liu, Jordan Grimstad, Mahmoud Alnahlawi, Katerina Tsihlas, Tom Hudson, Nikolai Grigorev, Yiling Jia, Terry Huang, Tobenna Peter Igwe, Sergei Lebedev, Xiaodan Tang, Igor Krivokon, Frankie Garcia, Melissa Tan, Eric Jia, Peter Stys, Shikhar Vashishth, Yu Liang, Balaji Venkatraman, Chenjie Gu, Anastasios Kementsietsidis, Chen Zhu, Junehyuk Jung, Yunfei Bai, Mohammad Javad Hosseini, Faruk Ahmed, Aditya Gupta, Xin Yuan, Shereen Ashraf, Shitij Nigam, Gautam Vasudevan, Pranjal Awasthi, Adi Mayrav Gilady, Zelda Mariet, Ramy Eskander, Haiguang Li, Hexiang Hu, Guillermo Garrido, Philippe Schlattner, George Zhang, Rohun Saxena, Petar Dević, Kritika Muralidharan, Ashwin Murthy, Yiqian Zhou, Min Choi, Arissa Wongpanich, Zhengdong Wang, Premal Shah, Yuntao Xu, Yiling Huang, Stephen Spencer, Alice Chen, James Cohan, Junjie Wang, Jonathan Tompson, Junru Wu, Ruba Haroun, Haiqiong Li, Blanca Huergo, Fan Yang, Tongxin Yin, James Wendt, Michael Bendersky, Rahma Chaabouni, Javier Snaider, Johan Ferret, Abhishek Jindal, Tara Thompson, Andrew Xue, Will Bishop, Shubham Milind Phal, Archit Sharma, Yunhsuan Sung, Prabakar Radhakrishnan, Mo Shomrat, Reeve Ingle, Roopali Vij, Justin Gilmer, Mihai Dorin Istin, Sam Sobell, Yang Lu, Emily Nottage, Dorsa Sadigh, Jeremiah Willcock, Tingnan Zhang, Steve Xu, Sasha Brown, Katherine Lee, Gary Wang, Yun Zhu, Yi Tay, Cheolmin Kim, Audrey Gutierrez, Abhanshu Sharma, Yongqin Xian, Sungyong Seo, Claire Cui, Elena Pochernina, Cip Baetu, Krzysztof Jastrzębski, Mimi Ly, Mohamed Elhawaty, Dan Suh, Eren Sezener, Pidong Wang, Nancy Yuen, George Tucker, Jiahao Cai, Zuguang Yang, Cindy Wang, Alex Muzio, Hai Qian, Jae Yoo, Derek Lockhart, Kevin R. McKee, Mandy Guo, Malika Mehrotra, Artur Mendonça, Sanket Vaibhav Mehta, Sherry Ben, Chetan Tekur, Jiaqi Mu, Muye Zhu, Victoria Krakovna, Hongrae Lee, AJ Maschinot, Sébastien Cevey, HyunJeong Choe, Aijun Bai, Hansa Srinivasan, Derek Gasaway, Nick Young, Patrick Siegler, Dan Holtmann-Rice, Vihari Piratla, Kate Baumli, Roey Yogev, Alex Hofer, Hado van Hasselt, Svetlana Grant, Yuri Chervonyi, David Silver, Andrew Hogue, Ayushi Agarwal, Kathie Wang, Preeti Singh, Four Flynn, Josh Lipschultz, Robert David, Lizzetth Bellot, Yao-Yuan Yang, Long Le, Filippo Graziano, Kate Olszewska, Kevin Hui, Akanksha Maurya, Nikos Parotsidis, Weijie Chen, Tayo Oguntebi, Joe Kelley, Anirudh Baddepudi, Johannes Mauerer, Gregory Shaw, Alex Siegman, Lin Yang, Shravya Shetty, Subhrajit Roy, Yunting Song, Wojciech Stokowiec, Ryan Burnell, Omkar Savant, Robert Busa-Fekete, Jin Miao, Samrat Ghosh, Liam MacDermed, Phillip Lippe, Mikhail Dektiarev, Zach Behrman, Fabian Mentzer, Kelvin Nguyen, Meng Wei, Siddharth Verma, Chris Knutsen, Sudeep Dasari, Zhipeng Yan, Petr Mitrichev, Xingyu Wang, Virat Shejwalkar, Jacob Austin, Srinivas Sunkara, Navneet Potti, Yan Virin, Christian Wright, Gaël Liu, Oriana Riva, Etienne Pot, Greg Kochanski, Quoc Le, Gargi Balasubramaniam, Arka Dhar, Yuguo Liao, Adam Bloniarz, Divyansh Shukla, Elizabeth Cole, Jong Lee, Sheng Zhang, Sushant Kafle, Siddharth Vashishtha, Parsa Mahmoudieh, Grace Chen, Raphael Hoffmann, Pranesh Srinivasan, Agustin Dal Lago, Yoav Ben Shalom, Zi Wang, Michael Elabd, Anuj Sharma, Junhyuk Oh, Suraj Kothawade, Maigo Le, Marianne Monteiro, Shentao Yang, Kaiz Alarakyia, Robert Geirhos, Diana Mincu, Håvard Garnes, Hayato Kobayashi, Soroosh Mariooryad, Kacper Krasowiak, Zhixin, Lai, Shibl Mourad, Mingqiu Wang, Fan Bu, Ophir Aharoni, Guanjie Chen, Abhimanyu Goyal, Vadim Zubov, Ankur Bapna, Elahe Dabir, Nisarg Kothari, Kay Lamerigts, Nicola De Cao, Jeremy Shar, Christopher Yew, Nitish Kulkarni, Dre Mahaarachchi, Mandar Joshi, Zhenhai Zhu, Jared Lichtarge, Yichao Zhou, Hannah Muckenhirn, Vittorio Selo, Oriol Vinyals, Peter Chen, Anthony Brohan, Vaibhav Mehta, Sarah Cogan, Ruth Wang, Ty Geri, Wei-Jen Ko, Wei Chen, Fabio Viola, Keshav Shivam, Lisa Wang, Madeleine Clare Elish, Raluca Ada Popa, Sébastien Pereira, Jianqiao Liu, Raphael Koster, Donnie Kim, Gufeng Zhang, Sayna Ebrahimi, Partha Talukdar, Yanyan Zheng, Petra Poklukar, Ales Mikhalap, Dale Johnson, Anitha Vijayakumar, Mark Omernick, Matt Dibb, Ayush Dubey, Qiong Hu, Apurv Suman, Vaibhav Aggarwal, Ilya Kornakov, Fei Xia, Wing Lowe, Alexey Kolganov, Ted Xiao, Vitaly Nikolaev, Steven Hemingray, Bonnie Li, Joana Iljazi, Mikołaj Rybiński, Ballie Sandhu, Peggy Lu, Thang Luong, Rodolphe Jenatton, Vineetha Govindaraj, Hui, Li, Gabriel Dulac-Arnold, Wonpyo Park, Henry Wang, Abhinit Modi, Jean Pouget-Abadie, Kristina Greller, Rahul Gupta, Robert Berry, Prajit Ramachandran, Jinyu Xie, Liam McCafferty, Jianling Wang, Kilol Gupta, Hyeontaek Lim, Blaž Bratanič, Andy Brock, Ilia Akolzin, Jim Sproch, Dan Karliner, Duhyeon Kim, Adrian Goedeckemeyer, Noam Shazeer, Cordelia Schmid, Daniele Calandriello, Parul Bhatia, Krzysztof Choromanski, Ceslee Montgomery, Dheeru Dua, Ana Ramalho, Helen King, Yue Gao, Lynn Nguyen, David Lindner, Divya Pitta, Oleaser Johnson, Khalid Salama, Diego Ardila, Michael Han, Erin Farnese, Seth Odoom, Ziyue Wang, Xiangzhuo Ding, Norman Rink, Ray Smith, Harshal Tushar Lehri, Eden Cohen, Neera Vats, Tong He, Parthasarathy Gopavarapu, Adam Paszke, Miteyan Patel, Wouter Van Gansbeke, Lucia Loher, Luis Castro, Maria Voitovich, Tamara von Glehn, Nelson George, Simon Niklaus, Zach Eaton-Rosen, Nemanja Rakićević, Erik Jue, Sagi Perel, Carrie Zhang, Yuval Bahat, Angéline Pouget, Zhi Xing, Fantine Huot, Ashish Shenoy, Taylor Bos, Vincent Coriou, Bryan Richter, Natasha Noy, Yaqing Wang, Santiago Ontanon, Siyang Qin, Gleb Makarchuk, Demis Hassabis, Zhuowan Li, Mandar Sharma, Kumaran Venkatesan, Iurii Kemaev, Roxanne Daniel, Shiyu Huang, Saloni Shah, Octavio Ponce, Warren, Chen, Manaal Faruqui, Jialin Wu, Slavica Andačić, Szabolcs Payrits, Daniel McDuff, Tom Hume, Yuan Cao, MH Tessler, Qingze Wang, Yinan Wang, Ivor Rendulic, Eirikur Agustsson, Matthew Johnson, Tanya Lando, Andrew Howard, Sri Gayatri Sundara Padmanabhan, Mayank Daswani, Andrea Banino, Michael Kilgore, Jonathan Heek, Ziwei Ji, Alvaro Caceres, Conglong Li, Nora Kassner, Alexey Vlaskin, Zeyu Liu, Alex Grills, Yanhan Hou, Roykrong Sukkerd, Gowoon Cheon, Nishita Shetty, Larisa Markeeva, Piotr Stanczyk, Tejas Iyer, Yuan Gong, Shawn Gao, Keerthana Gopalakrishnan, Tim Blyth, Malcolm Reynolds, Avishkar Bhoopchand, Misha Bilenko, Dero Gharibian, Vicky Zayats, Aleksandra Faust, Abhinav Singh, Min Ma, Hongyang Jiao, Sudheendra Vijayanarasimhan, Lora Aroyo, Vikas Yadav, Sarah Chakera, Ashwin Kakarla, Vilobh Meshram, Karol Gregor, Gabriela Botea, Evan Senter, Dawei Jia, Geza Kovacs, Neha Sharma, Sebastien Baur, Kai Kang, Yifan He, Lin Zhuo, Marija Kostelac, Itay Laish, Songyou Peng, Louis O'Bryan, Daniel Kasenberg, Girish Ramchandra Rao, Edouard Leurent, Biao Zhang, Sage Stevens, Ana Salazar, Ye Zhang, Ivan Lobov, Jake Walker, Allen Porter, Morgan Redshaw, Han Ke, Abhishek Rao, Alex Lee, Hoi Lam, Michael Moffitt, Jaeyoun Kim, Siyuan Qiao, Terry Koo, Robert Dadashi, Xinying Song, Mukund Sundararajan, Peng Xu, Chizu Kawamoto, Yan Zhong, Clara Barbu, Apoorv Reddy, Mauro Verzetti, Leon Li, George Papamakarios, Hanna Klimczak-Plucińska, Mary Cassin, Koray Kavukcuoglu, Rigel Swavely, Alain Vaucher, Jeffrey Zhao, Ross Hemsley, Michael Tschannen, Heming Ge, Gaurav Menghani, Yang Yu, Natalie Ha, Wei He, Xiao Wu, Maggie Song, Rachel Sterneck, Stefan Zinke, Dan A. Calian, Annie Marsden, Alejandro Cruzado Ruiz, Matteo Hessel, Almog Gueta, Benjamin Lee, Brian Farris, Manish Gupta, Yunjie Li, Mohammad Saleh, Vedant Misra, Kefan Xiao, Piermaria Mendolicchio, Gavin Buttimore, Varvara Krayvanova, Nigamaa Nayakanti, Matthew Wiethoff, Yash Pande, Azalia Mirhoseini, Ni Lao, Jasmine Liu, Yiqing Hua, Angie Chen, Yury Malkov, Dmitry Kalashnikov, Shubham Gupta, Kartik Audhkhasi, Yuexiang Zhai, Sudhindra Kopalle, Prateek Jain, Eran Ofek, Clemens Meyer, Khuslen Baatarsukh, Hana Strejček, Jun Qian, James Freedman, Ricardo Figueira, Michal Sokolik, Olivier Bachem, Raymond Lin, Dia Kharrat, Chris Hidey, Pingmei Xu, Dennis Duan, Yin Li, Muge Ersoy, Richard Everett, Kevin Cen, Rebeca Santamaria-Fernandez, Amir Taubenfeld, Ian Mackinnon, Linda Deng, Polina Zablotskaia, Shashank Viswanadha, Shivanker Goel, Damion Yates, Yunxiao Deng, Peter Choy, Mingqing Chen, Abhishek Sinha, Alex Mossin, Yiming Wang, Arthur Szlam, Susan Hao, Paul Kishan Rubenstein, Metin Toksoz-Exley, Miranda Aperghis, Yin Zhong, Junwhan Ahn, Michael Isard, Olivier Lacombe, Florian Luisier, Chrysovalantis Anastasiou, Yogesh Kalley, Utsav Prabhu, Emma Dunleavy, Shaan Bijwadia, Justin Mao-Jones, Kelly Chen, Rama Pasumarthi, Emily Wood, Adil Dostmohamed, Nate Hurley, Jiri Simsa, Alicia Parrish, Mantas Pajarskas, Matt Harvey, Ondrej Skopek, Yony Kochinski, Javier Rey, Verena Rieser, Denny Zhou, Sun Jae Lee, Trilok Acharya, Guowang Li, Joe Jiang, Xiaofan Zhang, Bryant Gipson, Ethan Mahintorabi, Marco Gelmi, Nima Khajehnouri, Angel Yeh, Kayi Lee, Loic Matthey, Leslie Baker, Trang Pham, Han Fu, Alex Pak, Prakhar Gupta, Cristina Vasconcelos, Adam Sadovsky, Brian Walker, Sissie Hsiao, Patrik Zochbauer, Andreea Marzoca, Noam Velan, Junhao Zeng, Gilles Baechler, Danny Driess, Divya Jain, Yanping Huang, Lizzie Tao, John Maggs, Nir Levine, Jon Schneider, Erika Gemzer, Samuel Petit, Shan Han, Zach Fisher, Dustin Zelle, Courtney Biles, Eugene Ie, Asya Fadeeva, Casper Liu, Juliana Vicente Franco, Adrian Collister, Hao Zhang, Renshen Wang, Ruizhe Zhao, Leandro Kieliger, Kurt Shuster, Rui Zhu, Boqing Gong, Lawrence Chan, Ruoxi Sun, Sujoy Basu, Roland Zimmermann, Jamie Hayes, Abhishek Bapna, Jasper Snoek, Weel Yang, Puranjay Datta, Jad Al Abdallah, Kevin Kilgour, Lu Li, SQ Mah, Yennie Jun, Morgane Rivière, Abhijit Karmarkar, Tammo Spalink, Tao Huang, Lucas Gonzalez, Duc-Hieu Tran, Averi Nowak, John Palowitch, Martin Chadwick, Ellie Talius, Harsh Mehta, Thibault Sellam, Philipp Fränken, Massimo Nicosia, Kyle He, Aditya Kini, David Amos, Sugato Basu, Harrison Jobe, Eleni Shaw, Qiantong Xu, Colin Evans, Daisuke Ikeda, Chaochao Yan, Larry Jin, Lun Wang, Sachin Yadav, Ilia Labzovsky, Ramesh Sampath, Ada Ma, Candice Schumann, Aditya Siddhant, Rohin Shah, John Youssef, Rishabh Agarwal, Natalie Dabney, Alessio Tonioni, Moran Ambar, Jing Li, Isabelle Guyon, Benny Li, David Soergel, Boya Fang, Georgi Karadzhov, Cristian Udrescu, Trieu Trinh, Vikas Raunak, Seb Noury, Dee Guo, Sonal Gupta, Mara Finkelstein, Denis Petek, Lihao Liang, Greg Billock, Pei Sun, David Wood, Yiwen Song, Xiaobin Yu, Tatiana Matejovicova, Regev Cohen, Kalyan Andra, David D'Ambrosio, Zhiwei Deng, Vincent Nallatamby, Ebrahim Songhori, Rumen Dangovski, Andrew Lampinen, Pankil Botadra, Adam Hillier, Jiawei Cao, Nagabhushan Baddi, Adhi Kuncoro, Toshihiro Yoshino, Ankit Bhagatwala, Marcáurelio Ranzato, Rylan Schaeffer, Tianlin Liu, Shuai Ye, Obaid Sarvana, John Nham, Chenkai Kuang, Isabel Gao, Jinoo Baek, Shubham Mittal, Ayzaan Wahid, Anita Gergely, Bin Ni, Josh Feldman, Carrie Muir, Pascal Lamblin, Wolfgang Macherey, Ethan Dyer, Logan Kilpatrick, Víctor Campos, Mukul Bhutani, Stanislav Fort, Yanif Ahmad, Aliaksei Severyn, Kleopatra Chatziprimou, Oleksandr Ferludin, Mason Dimarco, Aditya Kusupati, Joe Heyward, Dan Bahir, Kevin Villela, Katie Millican, Dror Marcus, Sanaz Bahargam, Caglar Unlu, Nicholas Roth, Zichuan Wei, Siddharth Gopal, Deepanway Ghoshal, Edward Lee, Sharon Lin, Jennie Lees, Dayeong Lee, Anahita Hosseini, Connie Fan, Seth Neel, Marcus Wu, Yasemin Altun, Honglong Cai, Enrique Piqueras, Josh Woodward, Alessandro Bissacco, Salem Haykal, Mahyar Bordbar, Prasha Sundaram, Sarah Hodkinson, Daniel Toyama, George Polovets, Austin Myers, Anu Sinha, Tomer Levinboim, Kashyap Krishnakumar, Rachita Chhaparia, Tatiana Sholokhova, Nitesh Bharadwaj Gundavarapu, Ganesh Jawahar, Haroon Qureshi, Jieru Hu, Nikola Momchev, Matthew Rahtz, Renjie Wu, Aishwarya P S, Kedar Dhamdhere, Meiqi Guo, Umang Gupta, Ali Eslami, Mariano Schain, Michiel Blokzijl, David Welling, Dave Orr, Levent Bolelli, Nicolas Perez-Nieves, Mikhail Sirotenko, Aman Prasad, Arjun Kar, Borja De Balle Pigem, Tayfun Terzi, Gellért Weisz, Dipankar Ghosh, Aditi Mavalankar, Dhruv Madeka, Kaspar Daugaard, Hartwig Adam, Viraj Shah, Dana Berman, Maggie Tran, Steven Baker, Ewa Andrejczuk, Grishma Chole, Ganna Raboshchuk, Mahdi Mirzazadeh, Thais Kagohara, Shimu Wu, Christian Schallhart, Bernett Orlando, Chen Wang, Alban Rrustemi, Hao Xiong, Hao Liu, Arpi Vezer, Nolan Ramsden, Shuo-yiin Chang, Sidharth Mudgal, Yan Li, Nino Vieillard, Yedid Hoshen, Farooq Ahmad, Ambrose Slone, Amy Hua, Natan Potikha, Mirko Rossini, Jon Stritar, Sushant Prakash, Zifeng Wang, Xuanyi Dong, Alireza Nazari, Efrat Nehoran, Kaan Tekelioglu, Yinxiao Li, Kartikeya Badola, Tom Funkhouser, Yuanzhen Li, Varun Yerram, Ramya Ganeshan, Daniel Formoso, Karol Langner, Tian Shi, Huijian Li, Yumeya Yamamori, Amayika Panda, Alaa Saade, Angelo Scorza Scarpati, Chris Breaux, CJ Carey, Zongwei Zhou, Cho-Jui Hsieh, Sophie Bridgers, Alena Butryna, Nishesh Gupta, Vaibhav Tulsyan, Sanghyun Woo, Evgenii Eltyshev, Will Grathwohl, Chanel Parks, Seth Benjamin, Rina Panigrahy, Shenil Dodhia, Daniel De Freitas, Chris Sauer, Will Song, Ferran Alet, Jackson Tolins, Cosmin Paduraru, Xingyi Zhou, Brian Albert, Zizhao Zhang, Lei Shu, Mudit Bansal, Sarah Nguyen, Amir Globerson, Owen Xiao, James Manyika, Tom Hennigan, Rong Rong, Josip Matak, Anton Bakalov, Ankur Sharma, Danila Sinopalnikov, Andrew Pierson, Stephen Roller, Geoff Brown, Mingcen Gao, Toshiyuki Fukuzawa, Amin Ghafouri, Kenny Vassigh, Iain Barr, Zhicheng Wang, Anna Korsun, Rajesh Jayaram, Lijie Ren, Tim Zaman, Samira Khan, Yana Lunts, Dan Deutsch, Dave Uthus, Nitzan Katz, Masha Samsikova, Amr Khalifa, Nikhil Sethi, Jiao Sun, Luming Tang, Uri Alon, Xianghong Luo, Dian Yu, Abhishek Nayyar, Bryce Petrini, Will Truong, Vincent Hellendoorn, Nikolai Chinaev, Chris Alberti, Wei Wang, Jingcao Hu, Vahab Mirrokni, Ananth Balashankar, Avia Aharon, Aahil Mehta, Ahmet Iscen, Joseph Kready, Lucas Manning, Anhad Mohananey, Yuankai Chen, Anshuman Tripathi, Allen Wu, Igor Petrovski, Dawsen Hwang, Martin Baeuml, Shreyas Chandrakaladharan, Yuan Liu, Rey Coaguila, Maxwell Chen, Sally Ma, Pouya Tafti, Susheel Tatineni, Terry Spitz, Jiayu Ye, Paul Vicol, Mihaela Rosca, Adrià Puigdomènech, Zohar Yahav, Sanjay Ghemawat, Hanzhao Lin, Phoebe Kirk, Zaid Nabulsi, Sergey Brin, Bernd Bohnet, Ken Caluwaerts, Aditya Srikanth Veerubhotla, Dan Zheng, Zihang Dai, Petre Petrov, Yichong Xu, Ramin Mehran, Zhuo Xu, Luisa Zintgraf, Jiho Choi, Spurthi Amba Hombaiah, Romal Thoppilan, Sashank Reddi, Lukasz Lew, Li Li, Kellie Webster, KP Sawhney, Lampros Lamprou, Siamak Shakeri, Mayank Lunayach, Jianmin Chen, Sumit Bagri, Alex Salcianu, Ying Chen, Yani Donchev, Charlotte Magister, Signe Nørly, Vitor Rodrigues, Tomas Izo, Hila Noga, Joe Zou, Thomas Köppe, Wenxuan Zhou, Kenton Lee, Xiangzhu Long, Danielle Eisenbud, Anthony Chen, Connor Schenck, Chi Ming To, Peilin Zhong, Emanuel Taropa, Minh Truong, Omer Levy, Danilo Martins, Zhiyuan Zhang, Christopher Semturs, Kelvin Zhang, Alex Yakubovich, Pol Moreno, Lara McConnaughey, Di Lu, Sam Redmond, Lotte Weerts, Yonatan Bitton, Tiziana Refice, Nicolas Lacasse, Arthur Conmy, Corentin Tallec, Julian Odell, Hannah Forbes-Pollard, Arkadiusz Socala, Jonathan Hoech, Pushmeet Kohli, Alanna Walton, Rui Wang, Mikita Sazanovich, Kexin Zhu, Andrei Kapishnikov, Rich Galt, Matthew Denton, Ben Murdoch, Caitlin Sikora, Kareem Mohamed, Wei Wei, Uri First, Tim McConnell, Luis C. Cobo, James Qin, Thi Avrahami, Daniel Balle, Yu Watanabe, Annie Louis, Adam Kraft, Setareh Ariafar, Yiming Gu, Eugénie Rives, Charles Yoon, Andrei Rusu, James Cobon-Kerr, Chris Hahn, Jiaming Luo, Yuvein, Zhu, Niharika Ahuja, Rodrigo Benenson, Raphaël Lopez Kaufman, Honglin Yu, Lloyd Hightower, Junlin Zhang, Darren Ni, Lisa Anne Hendricks, Gabby Wang, Gal Yona, Lalit Jain, Pablo Barrio, Surya Bhupatiraju, Siva Velusamy, Allan Dafoe, Sebastian Riedel, Tara Thomas, Zhe Yuan, Mathias Bellaiche, Sheena Panthaplackel, Klemen Kloboves, Sarthak Jauhari, Canfer Akbulut, Todor Davchev, Evgeny Gladchenko, David Madras, Aleksandr Chuklin, Tyrone Hill, Quan Yuan, Mukundan Madhavan, Luke Leonhard, Dylan Scandinaro, Qihang Chen, Ning Niu, Arthur Douillard, Bogdan Damoc, Yasumasa Onoe, Fabian Pedregosa, Fred Bertsch, Chas Leichner, Joseph Pagadora, Jonathan Malmaud, Sameera Ponda, Andy Twigg, Oleksii Duzhyi, Jingwei Shen, Miaosen Wang, Roopal Garg, Jing Chen, Utku Evci, Jonathan Lee, Leon Liu, Koji Kojima, Masa Yamaguchi, Arunkumar Rajendran, AJ Piergiovanni, Vinodh Kumar Rajendran, Marco Fornoni, Gabriel Ibagon, Harry Ragan, Sadh MNM Khan, John Blitzer, Andrew Bunner, Guan Sun, Takahiro Kosakai, Scott Lundberg, Ndidi Elue, Kelvin Guu, SK Park, Jane Park, Arunachalam Narayanaswamy, Chengda Wu, Jayaram Mudigonda, Trevor Cohn, Hairong Mu, Ravi Kumar, Laura Graesser, Yichi Zhang, Richard Killam, Vincent Zhuang, Mai Giménez, Wael Al Jishi, Ruy Ley-Wild, Alex Zhai, Kazuki Osawa, Diego Cedillo, Jialu Liu, Mayank Upadhyay, Marcin Sieniek, Roshan Sharma, Tom Paine, Anelia Angelova, Sravanti Addepalli, Carolina Parada, Kingshuk Majumder, Avery Lamp, Sanjiv Kumar, Xiang Deng, Artiom Myaskovsky, Tea Sabolić, Jeffrey Dudek, Sarah York, Félix de Chaumont Quitry, Jiazhong Nie, Dee Cattle, Alok Gunjan, Bilal Piot, Waleed Khawaja, Seojin Bang, Simon Wang, Siavash Khodadadeh, Raghavender R, Praynaa Rawlani, Richard Powell, Kevin Lee, Johannes Griesser, GS Oh, Cesar Magalhaes, Yujia Li, Simon Tokumine, Hadas Natalie Vogel, Dennis Hsu, Arturo BC, Disha Jindal, Matan Cohen, Zi Yang, Junwei Yuan, Dario de Cesare, Tony Bruguier, Jun Xu, Monica Roy, Alon Jacovi, Dan Belov, Rahul Arya, Phoenix Meadowlark, Shlomi Cohen-Ganor, Wenting Ye, Patrick Morris-Suzuki, Praseem Banzal, Gan Song, Pranavaraj Ponnuramu, Fred Zhang, George Scrivener, Salah Zaiem, Alif Raditya Rochman, Kehang Han, Badih Ghazi, Kate Lee, Shahar Drath, Daniel Suo, Antonious Girgis, Pradeep Shenoy, Duy Nguyen, Douglas Eck, Somit Gupta, Le Yan, Joao Carreira, Anmol Gulati, Ruoxin Sang, Daniil Mirylenka, Emma Cooney, Edward Chou, Mingyang Ling, Cindy Fan, Ben Coleman, Guilherme Tubone, Ravin Kumar, Jason Baldridge, Felix Hernandez-Campos, Angeliki Lazaridou, James Besley, Itay Yona, Neslihan Bulut, Quentin Wellens, AJ Pierigiovanni, Jasmine George, Richard Green, Pu Han, Connie Tao, Geoff Clark, Chong You, Abbas Abdolmaleki, Justin Fu, Tongzhou Chen, Ashwin Chaugule, Angad Chandorkar, Altaf Rahman, Will Thompson, Penporn Koanantakool, Mike Bernico, Jie Ren, Andrey Vlasov, Sergei Vassilvitskii, Maciej Kula, Yizhong Liang, Dahun Kim, Yangsibo Huang, Chengxi Ye, Dmitry Lepikhin, Wesley Helmholz

arXiv:2507.06261v6cs.CLcs.AI

TL;DR

The report examines how to deliver practical value with natively multimodal models that combine advanced reasoning with broad capability and cost coverage. It introduces the Gemini 2.X family with native thinking and multimodal training, finding that the models span the capability–cost frontier while Gemini 2.5 Pro is its most capable model.

  • Problem

    The report addresses how to build natively multimodal reasoning models that deliver practical value in complex software environments.

    Source: §1 · p. 1, Code · p. 6
  • Method

    The family combines native thinking across domains with curated multimodal instruction, preference, and tool-use data.

    Source: §2.2 · p. 4, §2.5 · p. 6
  • Results

    The Gemini 2.X models span the full capability–cost Pareto frontier, while Gemini 2.5 Pro is the most capable model developed by the authors.

    Source: §6 · p. 39
  • Takeaways & Limitations

    Gemini 2.X offers models covering varied capability and cost requirements, with Gemini 2.5 Pro targeting the highest capability level.

    Source: §6 · p. 39

    Evolving adversarial evaluation datasets make strict comparisons between model-family evaluations difficult.

    Source: Baseline Assurance · p. 27

Abstract

from arXiv · show

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

1. Introduction

The Gemini 2.X family introduces natively multimodal models with advanced reasoning, long-context inputs, and native tool use for complex agentic systems. Its models span capability–cost tradeoffs from highly intelligent reasoning to fast, cost-efficient at-scale usage, while Gemini 2.5 maintains robust safety performance.

Model family overview

  • The report presents Gemini 2.5 Pro and 2.5 Flash alongside Gemini 2.0 Flash and Flash-Lite as a next-generation family designed to power agentic systems and advance toward a universal AI assistant.The family builds on the Gemini 1.5 series (Gemini Team, 2024) and advances toward the vision of a universal AI assistant.Source: §1 · p. 1
  • Gemini 2.X models combine native multimodality, >1 million-token context, and native tool use to process text, audio, images, video, and code repositories for complex agentic systems.The capabilities support comprehension of vast datasets and are exemplified by Gemini Plays Pokémon1.Source: §1 · p. 1
  • The family covers the capability–cost frontier through Gemini 2.5 Pro’s reasoning and coding, 2.5 Flash’s controllable thinking budget, 2.0 Flash’s speed and efficiency, and 2.0 Flash-Lite’s at-scale cost efficiency.The models are presented as shifting the Pareto frontier across core capabilities, applications, and use cases; Table 1 provides a full comparison.Source: §1 · p. 1, Table 1 · p. 2

Safety

  • Gemini 2.5 models maintain robust safety and improve helpfulness and general tone over their 2.0 and 1.5 counterparts without interfering with important use cases.Gemini 2.5 Pro showed increased capabilities in some critical areas but did not reach any Critical Capability Level in CBRN, cybersecurity, machine learning R&D, or deceptive alignment.Source: §1 · pp. 1–2

2. Model Architecture, Training and Dataset

Gemini 2.5 combines sparse multimodal MoE transformers, long-context and native Thinking capabilities, improved data and post-training methods, and TPU-scale infrastructure. These advances extend coding, factuality, multilingual, audio, video, agentic, and reasoning capabilities while supporting efficient model variants.

2.1. Model Architecture

  • Gemini 2.5 uses sparse MoE transformers with native text, vision, and audio inputs, improving capacity–computation decoupling and training stability.The models dynamically route tokens to subsets of parameters, while architectural changes improve signal propagation and optimization dynamics.Source: §2.1 · p. 2
  • Gemini 2.5 supports long-context multimodal processing, including up to 1M-token inputs and videos lasting up to 3 hours.The models process long-form text, codebases, audio, and video; vision changes also enable converting demonstrative videos into interactive coding applications.Source: §2.1 · p. 3, Video · p. 8

2.2. Dataset

  • The pre-training data spans web documents, code, images, audio, and video, while post-training uses vetted multimodal instruction-response, preference, and tool-use data with improved filtering and deduplication.The 2.5 dataset cutoff is January 2025, and the post-training data emphasizes quality control across multimodal supervision and tool use.Source: §2.2 · pp. 3–4

2.3. Training Infrastructure

  • TPUv5p training infrastructure combines synchronous data parallelism with elasticity and rapid Silent Data Corruption detection to reduce interruption and debugging costs.Training continued at around 97% throughput during slice recovery; suspicious steps were replayed deterministically, and about 0.25% of steps were replayed for suspected SDCs, with 6% confirmed as corruption.Source: §2.3 · p. 4

2.4. Post-training

  • Post-training improvements combine higher-quality SFT, reward modeling, and RL data with more RL compute, verifiable and generative rewards, and more stable algorithms for complex tool-using environments.Both Gemini 2.5 Pro and Flash gained more than 110 LMArena Elo points over their Gemini 1.5 counterparts: 122 for Pro and 111 for Flash.Source: §2.4 · p. 5

2.5. Thinking

  • Thinking is trained natively across domains, allowing Gemini 2.5 to spend thousands of forward passes on reasoning and scale performance with inference-time compute.Thinking integrates with multimodal inputs and 1M+ token context; users can set a token budget to trade off performance and cost.Source: §2.5 · p. 6

Capability-specific improvements

  • Capability-specific training substantially improves coding, long-context reasoning, multilinguality, audio generation, video understanding, and web-based research.Examples include LiveCodeBench rising from 30.5% to 74.2%, Aider Polyglot from 16.9% to 82.2%, and SWEBench-verified from 34.2% to 67.2%; Deep Research rises from 7.95% to 26.9%, or 32.4% with higher compute.Source: Code · p. 7, Long context · pp. 7–8, Multilinguality · p. 8

2.7. The path to Gemini 2.5

3. Quantitative evaluation

The Gemini 2.5 family improves substantially over Gemini 1.5 across coding, math, reasoning, and image understanding, while Gemini 2.5 Pro achieves leading results against other language models and in audio and video understanding. Evaluations use decontamination procedures, defined testing protocols, and benchmark-specific sourcing and context-length conditions.

3.2. Core capability quantitative results

  • Gemini 2.5 models excel on coding benchmarks and improve markedly over previous Gemini models, while also raising AIME 2025 from 17.5% to 88.0% and GPQA diamond from 58.1% to 86.4%.Performance on image understanding tasks also increased significantly.Source: Figure 5 · p. 11, §3.2 · p. 12, Table 3 · p. 13

3. Quantitative evaluation

  • The evaluation mitigates leakage with n-gram, semantic-similarity, and model-based decontamination while supplementing public benchmarks with internal non-public evaluations such as HiddenMath.Non-Gemini results generally use provider-reported numbers, and SWE-bench Verified results may not be directly comparable because scaffolding and infrastructure differ.Source: §3 · p. 11, §3.1 · p. 12

3.1. Methodology

  • Gemini evaluations report pass@1 scores in single-attempt settings unless specified, use AI Studio API model IDs with default sampling, and average multiple trials for smaller benchmarks.Multiple-attempt settings allow test-time candidate selection; Aider Polyglot averages three trials and Vibe-Eval uses Gemini as a judge.Source: §3.1 · p. 12

3.3. Evaluation of Gemini 2.5 Pro against other large language models

  • Against the examined language models, Gemini 2.5 Pro leads Aider Polyglot, Humanity’s Last Exam, GPQA diamond, SimpleQA, FACTS Grounding, LOFT, and MRCR at 128k context, and uniquely supports 1M+ tokens.The comparisons are reported in Table 4, with LOFT and MRCR evaluated at both 128k and 1M context variants where applicable.Source: §3.3 · p. 14, Table 4 · p. 14

Audio Understanding

  • Gemini 2.5 Pro achieves state-of-the-art audio understanding on public ASR and AST benchmarks and compares favorably with alternatives under comparable prompts and inputs.The audio comparison includes earlier Gemini models and GPT models.Source: Audio Understanding · p. 14, Table 5 · p. 15

Video Understanding

  • Gemini 2.5 Pro achieves state-of-the-art performance on key video understanding benchmarks, surpassing GPT 4.1 under comparable testing conditions.Gemini 2.5 Flash provides a highly competitive alternative for cost-sensitive applications.Source: Video Understanding · pp. 14–15, Table 6 · p. 15

4. Example use cases of Gemini 2.5 Pro

Gemini 2.5 Pro demonstrates long-horizon agentic reasoning through autonomous Pokémon gameplay, while also transforming multimodal inputs into sophisticated applications and powering diverse Google products. These examples reveal both strong long-context capabilities and limitations in screen reading and generative reasoning over very large histories.

4.1. Gemini Plays Pokémon

  • Gemini 2.5 Pro completed Pokémon Blue autonomously, finishing the first run in 813 hours and the finalized second run in 406.5 hours.The second run used a fixed agentic harness and completed the game in nearly half the time of the first run.Source: §4.1 · p. 16

Capabilities assessment

  • The Pokémon agent solved complex puzzles and mazes, reasoning over 100K+ token contexts and finding paths of up to 150 actions.Examples included spinner puzzles, the Safari Zone, Route 13, and boulder puzzles in Victory Road and the Seafoam Islands.Source: Capabilities assessment · p. 17

Where does 2.5 Pro struggle while playing Pokémon?

  • Despite strong long-context performance, the agent struggled with raw Game Boy pixels and, beyond 100k tokens, sometimes repeated historical actions instead of synthesizing novel plans.Text translated from RAM was therefore necessary, while the million-token context frontier remains an active area for co-designing models and agent scaffolds.Source: Where does 2.5 Pro struggle while… · pp. 17–18

4.2. What else can Gemini 2.5 do?

  • Gemini 2.5 Pro converts unstructured inputs and images into interactive tools, accurate spatial representations, simulations, visualizations, educational utilities, and creative applications.Examples include line-practice tools from play scripts, bookshelf recommendation apps, image-to-SVG reconstruction, solar-system models, cartography tools, and photorealistic 3D interfaces.Source: §4.2 · p. 18

4.3. Gemini in Google Products

  • Gemini or customized Gemini versions are incorporated into Google products including Search, Project Astra, Gemini Deep Research, NotebookLM, Project Mariner, and Jules.The listed products span search, audiovisual dialogue, research assistance, podcast generation, web browsing, and coding assistance.Source: §4.3 · p. 18

5. Safety, Security, and Responsibility … 5.4. Results on Training/Development Evaluations

Gemini’s safety program combines policy and helpfulness criteria, safety-aware training, automated red teaming, held-out and external assurance evaluations, governance review, and development results showing safer but more helpful newer models with narrowly concentrated reviewed losses.

Guideline for Navigating This Section

  • The section guides readers from overall safety methodology through policies, safety training, development results, red teaming, privacy, frontier safety evaluations, and external testing.The listed sequence defines the scope of the merged safety sections.Source: Guideline for Navigating This Section · p. 19

5. Safety, Security, and Responsibility

  • Gemini’s safety program evaluates harmful-content avoidance, helpful fulfillment, respectful and objective behavior, and dangerous capabilities while using automated red teaming to improve training data and evaluations.Assurance evaluations are held out, conducted outside the development team, and supplemented by independent experts or a government body for models with new or significantly improved capabilities.Source: §5.1 · p. 19, §5.4 · p. 21

5.1. Our Process

  • Governance is integrated through Responsibility and Safety Council review of novel-capability assessments and assurance metrics, informing development guidance and release decisions.The Council reviews initial ethics and safety assessments and model-performance metrics from assurance evaluations.Source: §5.1 · p. 19

Safety policies

  • Gemini’s cross-modal safety policies prohibit child exploitation, hate speech, dangerous content, harassment, sexually explicit content, and medically unsupported advice, while security efforts target privacy leakage and prompt injection.These policies apply irrespective of input modality and aim to minimize harmful outputs such as suicide instructions or exposed personal data.Source: Safety policies · p. 20

Desiderata, aka “helpfulness”

  • Helpfulness desiderata prioritize fulfilling user goals when possible and responding respectfully without assuming bad intent when refusal is necessary.The model should refuse only when no policy-compliant response can fulfill the request.Source: Desiderata, aka “helpfulness” · p. 20

5.3. Training for Safety, Security, and Responsibility

  • Safety training converts policies and desiderata into automated metrics, using filtering, conditional pre-training, SFT, and RL*F with adversarial data, human feedback, critics, and continuous monitoring.The process addresses both policy violations and unnecessary refusals, while tracking safety and non-safety regressions across iterations.Source: §5.3 · pp. 20–21

5.4. Results on Training/Development Evaluations

  • Gemini 2.0 was substantially safer than Gemini 1.5 but over-refused benign requests, while Gemini 2.5 improves helpfulness and instruction following, with reviewed losses overwhelmingly false positives or non-egregious.Remaining losses were narrowly concentrated in sexually suggestive or hateful creative contexts, with no observed increase outside those contexts.Source: §5.4 · p. 21

5.5. Automated Red Teaming · 5.6. Memorization and Privacy

Automated red teaming scales dynamic safety and security evaluation, while Gemini 2.X shows reduced memorization and no detected personal information in memorized outputs. Gemini 2.5 further improves resilience to indirect prompt injection through adversarial training, although stronger models remain more challenging to secure.

For Safety

  • ART models evaluation as a multi-agent game in which attackers optimize policy-violating or unhelpful responses using judge-derived rewards.Attackers operate black-box through natural-language queries, while judges are prompted or finetuned Gemini models; seeds include policies, trending topics, and past escalations.Source: For Safety · p. 22
  • Automated red teaming generated thousands of informative examples per hour, discovering novel issues and accelerating mitigation, while Gemini 2.5 Flash and Pro achieved the strongest helpfulness results with robust safety metrics.ART supports evaluation of policy violations, tone, helpfulness, and neutrality before model and product releases.Source: For Safety · p. 22

For Security

  • Against indirect prompt injection, Gemini 2.0 models reduced attack success for Actor Critic and Beam Search but Gemini 2.0 Flash’s TAP success rate increased by 16.2% over already high Gemini 1.5 Flash rates.TAP exploits more creative natural-language scenarios, whereas Actor Critic and Beam Search use persuasive triggers or random-token search.Source: For Security · p. 24
  • Gemini 2.5 Flash and Pro were more resilient across all three indirect-prompt-injection techniques, attributed to adversarial training, although Pro remained less resilient than Flash.The authors continue evolving adversarial evaluations and training to monitor and improve security as model capabilities increase.Source: For Security · p. 24

Discoverable Memorization

  • Discoverable memorization was tested on over 700,000 training documents using 50-token prefixes and suffixes, classifying outputs as exact or approximately memorized at a 10% edit-distance threshold.The memorization rate is the ratio of generations matching training data among all sampled generations.Source: Discoverable Memorization · p. 25
  • Gemini 2.X memorized long-form text at much lower rates than prior Google models, with approximate memorization becoming more prevalent but decreasing over time.Figure 8 compares exact and approximate memorization across the model lineage; Gemini 2.0 Flash-Lite and Gemini 2.5 Flash particularly showed more approximate, less severe memorization.Source: Discoverable Memorization · p. 25, Figure 8 · p. 26
  • No personal information was observed in Gemini 2.X outputs classified as memorization, although the sensitive-data detector’s broad high-recall rules likely overestimate personal information.Personal information was counted at any severity level, and the analysis found a continuing overall decline in memorization.Source: Discoverable Memorization · p. 25, Figure 8 · p. 26

Extractable Memorization and Divergence

  • Divergence occurred roughly 69% of the time for Gemini 2.0 Flash and Flash-Lite and roughly 59% for Gemini 2.5, while only roughly 0.2% of successful divergences emitted memorized text.The memorized text was often boilerplate code or web content.Source: Extractable Memorization and Divergence · p. 26

5.7. Assurance Evaluations and Frontier Safety Framework

The section describes arms-length assurance evaluations for release governance and Frontier Safety Framework evaluations for severe-harm risks. Gemini 2.5 models met child-safety thresholds, generally reduced content-policy violations and ungrounded inferences, while Gemini 2.5 Pro did not reach FSF critical capability levels.

5.7. Assurance Evaluations and Frontier Safety Framework

  • Assurance evaluations are arms-length internal assessments conducted separately from model development to inform release decisions, with prompt sets held out to prevent overfitting.High-level findings are fed back to development teams, while results also inform product protections and Responsibility & Safety Council release review.Source: §5.7 · p. 26, Baseline Assurance · p. 27

Baseline Assurance

  • Changing adversarial datasets maintain evaluation quality and representativeness but make strict comparisons between model-family evaluations difficult.The report therefore provides qualitative assessments of evaluation trends over time.Source: Baseline Assurance · p. 27
  • Gemini 2.5 models met or improved upon child-safety launch thresholds and showed lower content-policy violation rates in most modalities than Gemini 1.5 and 2.0.Image-to-text had relatively higher violations, overall rates remained low, and violations tended to be slightly higher when thinking traces were visible.Source: Baseline Assurance · p. 27
  • Gemini 2.5 reduced ungrounded inferences about people in image understanding relative to Gemini 1.5, but refusal behaviour remained uneven across skin tones.Models were more likely to make ungrounded inferences about lighter-skinned people, while otherwise behaving similarly to Gemini 1.5 on unfair-bias evaluations.Source: Baseline Assurance · p. 27

Frontier Safety Framework Evaluations

  • Across all Frontier Safety Framework areas, Critical Capability Levels were not reached, so Gemini 2.5 Pro is unlikely to pose significant risk of severe harm.The FSF evaluates CBRN, cybersecurity, machine learning R&D, and deceptive-alignment risks using regular testing and earlier alert thresholds.Source: Table 10 · p. 28

CCL Evaluation Results

Gemini 2.5 Pro did not reach any evaluated Critical Capability Level, although it showed substantial capability increases and triggered an early-warning threshold for Cyber Uplift Level 1. Evaluations covered CBRN, cybersecurity, machine-learning R&D, and deceptive alignment, motivating more frequent testing and accelerated mitigations.

CCL Evaluation Results

  • Gemini 2.5 Pro did not reach any CCL, but its cyber capabilities reached the Cyber Uplift 1 alert threshold, prompting more frequent testing and accelerated mitigations.For other CCLs, models developed before the next regular testing interval were considered unlikely to reach the threshold.Source: CCL Evaluation Results · p. 28, Frontier Safety: Summary · pp. 35–36

Cybersecurity

  • Gemini 2.5 Pro solved 6/12 hard key-skills challenges, yet did not reach either Cybersecurity CCL and still could not consistently complete roughly half of medium and hard challenges.The key-skills benchmark covered reconnaissance, tool development, tool usage, and operational security; conventional CTF evaluations were saturated or too difficult to provide much comparative signal.Source: Cybersecurity · pp. 30–31, Figure 11 · p. 32, Figure 10 · p. 32

Machine Learning R&D

  • Gemini 2.5 Pro’s best RE-Bench runs scored 50% to 125% of the best human-written solutions, but it remained below the machine-learning R&D autonomy alert threshold.The benchmark contains relatively low-context, limited-time-horizon tasks, and Gemini 2.5 Pro exceeded expert reference performance in two cases despite lower average performance than the human baseline.Source: Machine Learning R&D · p. 33, Figure 12 · p. 34, Frontier Safety: Summary · p. 35

Deceptive Alignment

  • Gemini 2.5 Pro did not reach either instrumental-reasoning CCL, showing no successes on 8 of 11 situational-awareness evaluations and moderate but limited stealth performance.Across 50 trials, its highest situational-awareness result was 42% on Disabled Tool; stealth success was ~44% on Decision Sabotage and ~35% on Oversight Pattern.Source: Deceptive Alignment · pp. 34–35

Frontier Safety: Summary

  • Across CBRN, cybersecurity, machine-learning R&D, and deceptive alignment, Gemini 2.5 Pro showed capabilities in every area without reaching a CCL, while some best ML results exceeded expert references.The evaluation program will continue regularly to identify where mitigations such as refusing dangerous requests should be prioritized.Source: Frontier Safety: Summary · pp. 35–36

5.8. External Safety Testing

External safety testing used independent groups to probe the most capable Gemini models across autonomous systems, cybersecurity, prompt injection, chemical and biological, radiological and nuclear, and societal risks. Findings informed mitigation, governance, and gaps in internal evaluations, while generally indicating limited actionability for severe harms despite notable capabilities.

5.8. External Safety Testing

  • External testing covered only Gemini 2.0 Pro and 2.5 Pro, focusing on 2.5 Pro Preview 05-06 rather than the final GA candidate, and excluded Flash models.Independent groups used black-box access, developed domain-specific methods, and conducted qualitative red teaming or bespoke automated evaluations.Source: §5.8 · p. 36

Autonomous systems risks

  • External testing found Gemini 2.5 Pro had similar scheming capability to other evaluated models, with possible minor reward-hacking harms but insufficient capability for catastrophic harms during scheming rollouts.Deceptive-alignment evaluations further indicated low severe-harm risk because of limited situational awareness.Source: Autonomous systems risks · p. 37

Cybersecurity risks

  • Gemini 2.5 Pro showed marked cybersecurity capability increases over Gemini 1.5 Pro, including capability and throughput uplift across vulnerability discovery, exploitation, social engineering, and attack planning.External and Google DeepMind Cyber team evaluations found similarly high capability levels.Source: Cybersecurity risks · p. 37

Indirect Prompt Injections

  • Testing examined indirect prompt-injection susceptibility in function calls, security-measure asymmetries, and domain-dependent hijack rates, motivating continued monitoring and resilience measurement.This work complemented internal evaluations and mitigations for increasingly capable Gemini models.Source: Indirect Prompt Injections · pp. 37–38

Chemical and Biological risks

  • In chemical and biological scenarios, Gemini 2.5 Pro sometimes produced accurate, detailed experimentation and problem-solving information, but its steps were too broad to enable malicious actors.Experts role-played malign actors and graded proposed plans for scientific and logistical feasibility.Source: Chemical and Biological risks · p. 38

Radiological and Nuclear risks

  • Radiological and nuclear responses were accurate but lacked sufficient technical detail to be actionable under structured red-team assessments of threat actors and harm pathways.Evaluations used broad single-turn exploration and targeted multi-turn probing, assessing accuracy, actionability, and dual-use potential.Source: Radiological and Nuclear risks · p. 38

Societal risks

  • Societal-risk testing assessed democratic harms and radicalisation by measuring harmful-input identification and compliance with harmful requests, with findings shared for monitoring and mitigation.The evaluations focused on malicious-actor use of Gemini 2.5 Pro Preview 05-06 and addressed harms not mirrored by internal evaluations.Source: Societal risks · p. 38

6. Discussion

The Gemini 2.X family spans the capability–cost frontier, with Gemini 2.5 Pro delivering the strongest performance and new multimodal and agentic capabilities. The discussion also emphasizes strong safety and the urgent need for evaluations that keep pace with rapidly improving reasoning agents.

  • Gemini 2.X spans the full model capability–cost Pareto frontier, while Gemini 2.5 Pro is the company’s most capable model and excels in coding, math, and reasoning.It achieves extremely competitive scores on Aider Polyglot, GPQA (diamond), and Humanity’s Last Exam.Source: §6 · p. 39
  • Gemini 2.5 enables new applications, including lecture-video systems that generate interactive web applications for testing students’ knowledge.The models also support new agentic workflows and power numerous Google products already.Source: §6 · p. 39
  • Gemini 2.5 maintains strong safety standards, improves helpfulness over Gemini 1.5, and increases Critical Capabilities without crossing any Critical Capability Levels.Compared with its 1.5 counterparts, it is less likely to refuse important queries or respond in an overly sanctimonious tone.Source: §6 · p. 39
  • Scaling evaluations for future AI systems requires broader capability coverage, greater difficulty, and economically valuable tasks, especially for tool-using, self-critiquing agentic systems.Longer-running agents with tools and self-critique dramatically increase the complexity of measuring performance.Source: §6 · p. 39

7. Contributors and Acknowledgments

This section acknowledges the broad collaborative effort behind Gemini’s development. It presents an extended roster of contributors and recognizes the roles of Google teams and an independent developer.

  • The contributor roster begins with Gheorghe Comanici, Eric Bieber, Mike Schaekermann, and many additional contributors.The opening acknowledgment paragraph lists the first group of contributors.Source: §7 · p. 47
  • The acknowledgment continues with further contributors including Kristen Chiafullo, Andre Elisseeff, Nilpa Jha, and Prateek Kolhar.A second paragraph extends the named contributor list.Source: §7 · p. 47
  • Additional paragraphs continue the roster with contributors including Kashyap Kolipaka, Jason Chang, Eugen Vušak, and Srinivasan Venkatachary.The list proceeds through many more named contributors in subsequent paragraphs.Source: §7 · p. 47

Collaborative development

  • Over 3,000 Google researchers, engineers, and operations staff contributed to Gemini across research, architecture, data, training, infrastructure, evaluation, safety, and security.The contributor list is ordered randomly, and the report credits their collective dedication and expertise for making Gemini a reality.Source: §7 · p. 62

External contribution

  • Independent developer Joel Zhang is acknowledged for developing Gemini Plays Pokémon and sharing the design of its setup.Source: §7 · p. 62

8. Appendix

The appendix documents benchmark definitions, evaluation procedures, subsets, variants, and model specifications, while reporting that changing the model strongly affected Gemini Plays Pokémon performance. It also details evaluation conditions spanning coding, long-context, multimodal, speech, and video tasks.

8.1. Evaluation additional details

  • Agentic coding evaluations use tools for repository navigation, file editing, and testing, reporting single-attempt and reranked multiple-attempt modes.Evaluations use temperature=1, topp=0.99, and topk=1024; the tasks are drawn from real-world GitHub programming problems.Source: §8.1 · p. 63
  • MRCR-V2 uses a harder 8-needle, depth-3 formulation than earlier results and reports both comparable up-to-128K and full-length 1M-context variants.The added style parameter increases dictionary nesting relative to MRCR-V1 (Vodrahalli et al., 2024).Source: §8.1 · p. 64
  • Speech and video evaluations specify task-dependent zero- or few-shot settings, public-API evaluation, language subsets, scoring metrics, and frame limits up to 7200 frames.FLEURS uses WER or CER, CoVoST 2 reports BLEU for 21 languages, and video benchmarks use task-specific frame sampling.Source: §8.1 · p. 65
  • Table 11 summarizes the benchmarks used and their evaluation subsets, variants, and model specifications.The appendix directs readers to Table 11 for benchmark descriptions and details behind main-text scores.Source: §8.1 · p. 63, Table 11 · p. 66

8.2. Gemini Plays Pokémon Additional Details

  • Changing the model used by the Gemini Plays Pokémon agent had a strong effect on performance.The appendix points to Figure 4.1 for this comparison.Source: §8.2 · p. 66

Additional Harness Details

The Pokémon-playing agent combines structured game-state context, hierarchical memory, recurring guidance, exploration tracking, and specialized tools to support gameplay. A model comparison uses the same harness and starter while measuring progress in hours to account for action-speed differences.

Gemini Plays Pokémon harness

  • The agent receives RAM data overlaid with screenshots, gameplay instructions, translated button actions, hierarchical summaries, and explicit primary, secondary, tertiary, and contingency goals.Action history is summarized every 100 turns, and existing summaries are recompressed every 1000 turns.Source: Additional Harness Details · p. 66

Guidance and map memory

  • Every 25 turns, Guidance Gemini critiques the main agent’s performance and hallucinations, while an XML fog-of-war map records explored coordinates, visit counts, terrain types, and warp points.The system prompt instructs Gemini to explore, and unseen coordinates remain unavailable until explored.Source: Additional Harness Details · p. 66

Model comparison

  • Figure 13 compares different Gemini models using the same agentic harness and Charmander starter, with gameplay measured in hours to account for differences in action speed.An X marks gameplay termination and lower-bounds the time needed to reach the next milestone.Source: Figure 13 · p. 67

Agentic tools

  • Two specialized Gemini tools provide pathfinding and boulder-puzzle solving through prompted mental simulation and validation against available game information.The boulder-puzzle tool was added after the agent solved 2/4 Victory Road puzzles independently but progressed slowly on the third and fourth.Source: Additional Harness Details · p. 67

Additional Examples of Capabilities

Gemini 2.5 Pro demonstrates strong reasoning and long-context planning in Pokémon Blue, solving complex puzzles, recovering from an unprecedented softlock, and completing multi-step progression tasks. Its agentic tooling supports navigation and boulder-puzzle solving from textual descriptions, while longer-horizon runs show effective strategic adaptation.

Long Context Agentic Tooling

  • Gemini 2.5 Pro solved long textual pathfinding tasks across mazes, resource-limited maps, and multi-map boulder puzzles, outperforming Gemini 2.5 Flash on these tasks.The evaluated tasks included Rocket Hideout, Safari Zone, Route 13, and Seafoam Islands.Source: Additional Examples of Capabilities · p. 67
  • Gemini 2.5 Pro one-shotted some complex multi-level Sokoban-like boulder puzzles using only descriptions of boulder physics and path verification.The boulder_puzzle_strategist tool solves these puzzles in Victory Road.Source: Additional Examples of Capabilities · p. 68, Figure 14 · p. 68

General Reasoning

  • Gemini 2.5 Pro caught a fleeing Abra by planning Thunder Wave to reduce teleportation likelihood and improve the catching rate.The agent succeeded after multiple attempts.Source: Additional Examples of Capabilities · p. 68
  • After 4 hours of failed escape attempts, Gemini 2.5 Pro creatively used FLY to escape a Cycling Road softlock that could not occur in an existing game.Movement, ESCAPE ROPE, and DIG were blocked, whereas FLY enabled travel to a previously visited town.Source: Additional Examples of Capabilities · p. 69

Long Horizon Task Coherence

  • Gemini 2.5 Pro sustained multi-step progression by leveling Pikachu and Bellsprout for over 24 hours, acquiring CUT and FLASH through chained prerequisites, and solving Seafoam Islands’ five-floor puzzle.The Seafoam Islands challenge required tracking goals across five maps and using boulders to block currents.Source: Additional Examples of Capabilities · pp. 69–70
  • In 17 attempts in run 1 and 5 attempts in run 2, Gemini 2.5 Pro obtained both required Safari Zone HMs despite four maps, a 500-step limit, and a 500¥ entry cost.Failure would require restarting after losing the entry fee.Source: Additional Examples of Capabilities · p. 69

Additional Challenges

Gemini 2.5 Pro’s gameplay exposes failure modes involving hallucination-driven fixations, misleading context, detour-heavy puzzles, and panic-like reasoning degradation, although explicit puzzle-solving instructions can help under limited context.

Hallucinations and Fixations on Delusions

  • Hallucinated knowledge can fixate Gemini 2.5 Pro on impossible objectives, exemplified by spending many hours seeking the nonexistent TEA item from Pokémon FireRed/LeafGreen in Pokémon Red/Blue.The model confused events across Pokémon generations and repeatedly attempted to retrieve or give TEA to the guard.Source: Additional Challenges · p. 70
  • Explicitly prompting the model to disregard prior game knowledge partially reduced hallucinations from other games, but also impaired useful common-knowledge recall at critical points.This intervention was used in Run 2 to test reasoning through the game more cleanly.Source: Additional Challenges · p. 70
  • Context poisoning can embed misinformation across goals and summaries, causing Gemini 2.5 Pro to ignore common sense, repeat errors, pursue impossible goals, and adopt costly strategies such as blacking out.These fixations are also related to looping behavior and can take a long time to undo.Source: Additional Challenges · pp. 70–71

Topological Traps in Thinking Patterns

  • Topological traps place an apparent attractor near the player while requiring a detour, recurring in the Rocket Hideout spinner, Route 13 maze, and Victory Road 3F boulder puzzle.The correct solutions require ignoring nearby items, paths, ladders, exits, or boulder configurations.Source: Additional Challenges · p. 71
  • A pathfinder instruction lets Gemini 2.5 Pro solve the B3F spinner trap in one shot when the context is not too long.This indicates that explicit puzzle-solving guidance can overcome the trap under limited context.Source: Additional Challenges · p. 71

Agent Panic

  • Low party health or power points can trigger “agent panic,” during which Gemini 2.5 Pro repeatedly urges healing or escape and sometimes forgets to use the pathfinder tool.This state has appeared often enough for Twitch viewers to recognize its associated degradation in reasoning.Source: Additional Challenges · p. 71

Actions vs. Game Milestones

The section reports action-based game-milestone measurements, correctness and safety checks, improved image-to-SVG reconstruction by Gemini 2.5 Pro, and stronger long-context video-scene recall than Gemini 1.5 Pro.

Actions vs. Game Milestones

  • The evaluation plots the number of button-press actions or steps required to reach each game milestone, but action counts should be interpreted alongside time and cost.An action is a bucketed instance in which the agent outputs a sequence of button presses, and definitions may differ across agents.Source: Actions vs. Game Milestones · p. 71, Figure 15 · p. 72

8.3. Frontier Safety Framework Evaluations Additional Details: Frontier Safety Correctness Tests

  • Correctness checks combined AI and manual reviews, inspected representative benchmark trajectories and cybersecurity attempts, and found no errors believed to invalidate the benchmark results.AI assistance also monitored for obvious cheating, and none was found; the best RE-Bench trajectory was checked for reward hacking.Source: §8.3 · pp. 71–72

8.4. Image to Code Demo

  • Gemini 2.5 Pro generated better image-to-SVG reconstructions than Gemini 1.5 Pro.Both models were prompted to generate an SVG representation of an image.Source: §8.4 · p. 72, Figure 16 · p. 72

8.5. Long Context Video Understanding Demo

  • Gemini 2.5 Pro identified the video’s shirt color in 3/3 cases and the timestamp in 1/3, with the remaining 2/3 within 3 seconds; Gemini 1.5 Pro achieved 1/3 and 0/3.The evaluation used a 46-minute video and asked for a one-second scene’s shirt color and timecode.Source: §8.5 · p. 73, Table 12 · p. 73
Loading 2507.06261v6…