Staff View: :: Library Catalog

Saved in:

Bibliographic Details
Main Authors:	NVIDIA, :, Deshmukh, Amala Sanjay, Chumachenko, Kateryna, Rintamaki, Tuomas, Le, Matthieu, Poon, Tyler, Taheri, Danial Mohseni, Karmanov, Ilia, Liu, Guilin, Seppanen, Jarno, Chen, Guo, Sapra, Karan, Yu, Zhiding, Renduchintala, Adi, Wang, Charles, Jin, Peter, Goel, Arushi, Ranzinger, Mike, Voegtle, Lukas, Fischer, Philipp, Roman, Timo, Ping, Wei, Wang, Boxin, Yang, Zhuolin, Lee, Nayeon, Zhang, Shaokun, Liu, Fuxiao, Li, Zhiqi, Zhang, Di, Heinrich, Greg, Yin, Hongxu, Han, Song, Molchanov, Pavlo, Mannan, Parth, Xu, Yao, Scowcroft, Jane Polak, Balough, Tom, Radhakrishnan, Subhashree, Zhang, Paris, Cha, Sean, Kumar, Ratnesh, Bhat, Zaid Pervaiz, Zhang, Jian, Hanley, Darragh, Biswas, Pritam, Oliver, Jesse, Vasques, Kevin, Waleffe, Roger, Riach, Duncan, Olabiyi, Oluwatobi, Mahabaleshwarkar, Ameya Sunil, Kartal, Bilal, Gundecha, Pritam, Nguyen, Khanh, Milesi, Alexandre, Khvedchenia, Eugene, Zilberstein, Ran, Masad, Ofri, Bagrov, Natan, Assaf, Nave, Asida, Tomer, Afrimi, Daniel, Zuker, Amit, Haber, Netanel, Cheng, Zhiyu, Xin, Jingyu, Wu, Di, Spirin, Nik, Moosaei, Maryam, Ageev, Roman, Shah, Vanshil Atul, Wu, Yuting, Korzekwa, Daniel, Sreekumar, Unnikrishnan Kizhakkemadam, Jiang, Wanli, Subramanian, Padmavathy, Rico, Alejandra, Bhaskar, Sandip, Motiian, Saeid, Wu, Kedi, Surla, Annie, Chen, Chia-Chih, Wolff, Hayden, Feinberg, Matthew, Corpuz, Melissa, Wawrzos, Marek, Long, Eileen, Jhunjhunwala, Aastha, Hendricks, Paul, Memarian, Farzan, Hall, Benika, Wang, Xin-Yu, Mosallanezhad, David, Singhal, Soumye, Vega, Luis, Cheung, Katherine, Pawelec, Krzysztof, Evans, Michael, Luna, Katherine, Lou, Jie, Galinkin, Erick, Hazare, Akshay, Purandare, Kaustubh, Guan, Ann, Warno, Anna, Cui, Chen, Suhara, Yoshi, Likhite, Shibani, Mard, Seph, Price, Meredith, Sleiman, Laya, Kaji, Saori, Karpas, Udi, Briski, Kari, Conway, Joey, Lightstone, Michael, Kautz, Jan, Shoeybi, Mohammad, Patwary, Mostofa, Cohen, Jonathen, Kuchaiev, Oleksii, Tao, Andrew, Catanzaro, Bryan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	https://arxiv.org/abs/2511.03929
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866918189914390528
author	NVIDIA : Deshmukh, Amala Sanjay Chumachenko, Kateryna Rintamaki, Tuomas Le, Matthieu Poon, Tyler Taheri, Danial Mohseni Karmanov, Ilia Liu, Guilin Seppanen, Jarno Chen, Guo Sapra, Karan Yu, Zhiding Renduchintala, Adi Wang, Charles Jin, Peter Goel, Arushi Ranzinger, Mike Voegtle, Lukas Fischer, Philipp Roman, Timo Ping, Wei Wang, Boxin Yang, Zhuolin Lee, Nayeon Zhang, Shaokun Liu, Fuxiao Li, Zhiqi Zhang, Di Heinrich, Greg Yin, Hongxu Han, Song Molchanov, Pavlo Mannan, Parth Xu, Yao Scowcroft, Jane Polak Balough, Tom Radhakrishnan, Subhashree Zhang, Paris Cha, Sean Kumar, Ratnesh Bhat, Zaid Pervaiz Zhang, Jian Hanley, Darragh Biswas, Pritam Oliver, Jesse Vasques, Kevin Waleffe, Roger Riach, Duncan Olabiyi, Oluwatobi Mahabaleshwarkar, Ameya Sunil Kartal, Bilal Gundecha, Pritam Nguyen, Khanh Milesi, Alexandre Khvedchenia, Eugene Zilberstein, Ran Masad, Ofri Bagrov, Natan Assaf, Nave Asida, Tomer Afrimi, Daniel Zuker, Amit Haber, Netanel Cheng, Zhiyu Xin, Jingyu Wu, Di Spirin, Nik Moosaei, Maryam Ageev, Roman Shah, Vanshil Atul Wu, Yuting Korzekwa, Daniel Sreekumar, Unnikrishnan Kizhakkemadam Jiang, Wanli Subramanian, Padmavathy Rico, Alejandra Bhaskar, Sandip Motiian, Saeid Wu, Kedi Surla, Annie Chen, Chia-Chih Wolff, Hayden Feinberg, Matthew Corpuz, Melissa Wawrzos, Marek Long, Eileen Jhunjhunwala, Aastha Hendricks, Paul Memarian, Farzan Hall, Benika Wang, Xin-Yu Mosallanezhad, David Singhal, Soumye Vega, Luis Cheung, Katherine Pawelec, Krzysztof Evans, Michael Luna, Katherine Lou, Jie Galinkin, Erick Hazare, Akshay Purandare, Kaustubh Guan, Ann Warno, Anna Cui, Chen Suhara, Yoshi Likhite, Shibani Mard, Seph Price, Meredith Sleiman, Laya Kaji, Saori Karpas, Udi Briski, Kari Conway, Joey Lightstone, Michael Kautz, Jan Shoeybi, Mohammad Patwary, Mostofa Cohen, Jonathen Kuchaiev, Oleksii Tao, Andrew Catanzaro, Bryan
author_facet	NVIDIA : Deshmukh, Amala Sanjay Chumachenko, Kateryna Rintamaki, Tuomas Le, Matthieu Poon, Tyler Taheri, Danial Mohseni Karmanov, Ilia Liu, Guilin Seppanen, Jarno Chen, Guo Sapra, Karan Yu, Zhiding Renduchintala, Adi Wang, Charles Jin, Peter Goel, Arushi Ranzinger, Mike Voegtle, Lukas Fischer, Philipp Roman, Timo Ping, Wei Wang, Boxin Yang, Zhuolin Lee, Nayeon Zhang, Shaokun Liu, Fuxiao Li, Zhiqi Zhang, Di Heinrich, Greg Yin, Hongxu Han, Song Molchanov, Pavlo Mannan, Parth Xu, Yao Scowcroft, Jane Polak Balough, Tom Radhakrishnan, Subhashree Zhang, Paris Cha, Sean Kumar, Ratnesh Bhat, Zaid Pervaiz Zhang, Jian Hanley, Darragh Biswas, Pritam Oliver, Jesse Vasques, Kevin Waleffe, Roger Riach, Duncan Olabiyi, Oluwatobi Mahabaleshwarkar, Ameya Sunil Kartal, Bilal Gundecha, Pritam Nguyen, Khanh Milesi, Alexandre Khvedchenia, Eugene Zilberstein, Ran Masad, Ofri Bagrov, Natan Assaf, Nave Asida, Tomer Afrimi, Daniel Zuker, Amit Haber, Netanel Cheng, Zhiyu Xin, Jingyu Wu, Di Spirin, Nik Moosaei, Maryam Ageev, Roman Shah, Vanshil Atul Wu, Yuting Korzekwa, Daniel Sreekumar, Unnikrishnan Kizhakkemadam Jiang, Wanli Subramanian, Padmavathy Rico, Alejandra Bhaskar, Sandip Motiian, Saeid Wu, Kedi Surla, Annie Chen, Chia-Chih Wolff, Hayden Feinberg, Matthew Corpuz, Melissa Wawrzos, Marek Long, Eileen Jhunjhunwala, Aastha Hendricks, Paul Memarian, Farzan Hall, Benika Wang, Xin-Yu Mosallanezhad, David Singhal, Soumye Vega, Luis Cheung, Katherine Pawelec, Krzysztof Evans, Michael Luna, Katherine Lou, Jie Galinkin, Erick Hazare, Akshay Purandare, Kaustubh Guan, Ann Warno, Anna Cui, Chen Suhara, Yoshi Likhite, Shibani Mard, Seph Price, Meredith Sleiman, Laya Kaji, Saori Karpas, Udi Briski, Kari Conway, Joey Lightstone, Michael Kautz, Jan Shoeybi, Mohammad Patwary, Mostofa Cohen, Jonathen Kuchaiev, Oleksii Tao, Andrew Catanzaro, Bryan
contents	We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, datasets, and training recipes. Nemotron Nano V2 VL builds on Nemotron Nano V2, a hybrid Mamba-Transformer LLM, and innovative token reduction techniques to achieve higher inference throughput in long document and video scenarios. We are releasing model checkpoints in BF16, FP8, and FP4 formats and sharing large parts of our datasets, recipes and training code.
format	Preprint
id	arxiv_https___arxiv_org_abs_2511_03929
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	NVIDIA Nemotron Nano V2 VL NVIDIA : Deshmukh, Amala Sanjay Chumachenko, Kateryna Rintamaki, Tuomas Le, Matthieu Poon, Tyler Taheri, Danial Mohseni Karmanov, Ilia Liu, Guilin Seppanen, Jarno Chen, Guo Sapra, Karan Yu, Zhiding Renduchintala, Adi Wang, Charles Jin, Peter Goel, Arushi Ranzinger, Mike Voegtle, Lukas Fischer, Philipp Roman, Timo Ping, Wei Wang, Boxin Yang, Zhuolin Lee, Nayeon Zhang, Shaokun Liu, Fuxiao Li, Zhiqi Zhang, Di Heinrich, Greg Yin, Hongxu Han, Song Molchanov, Pavlo Mannan, Parth Xu, Yao Scowcroft, Jane Polak Balough, Tom Radhakrishnan, Subhashree Zhang, Paris Cha, Sean Kumar, Ratnesh Bhat, Zaid Pervaiz Zhang, Jian Hanley, Darragh Biswas, Pritam Oliver, Jesse Vasques, Kevin Waleffe, Roger Riach, Duncan Olabiyi, Oluwatobi Mahabaleshwarkar, Ameya Sunil Kartal, Bilal Gundecha, Pritam Nguyen, Khanh Milesi, Alexandre Khvedchenia, Eugene Zilberstein, Ran Masad, Ofri Bagrov, Natan Assaf, Nave Asida, Tomer Afrimi, Daniel Zuker, Amit Haber, Netanel Cheng, Zhiyu Xin, Jingyu Wu, Di Spirin, Nik Moosaei, Maryam Ageev, Roman Shah, Vanshil Atul Wu, Yuting Korzekwa, Daniel Sreekumar, Unnikrishnan Kizhakkemadam Jiang, Wanli Subramanian, Padmavathy Rico, Alejandra Bhaskar, Sandip Motiian, Saeid Wu, Kedi Surla, Annie Chen, Chia-Chih Wolff, Hayden Feinberg, Matthew Corpuz, Melissa Wawrzos, Marek Long, Eileen Jhunjhunwala, Aastha Hendricks, Paul Memarian, Farzan Hall, Benika Wang, Xin-Yu Mosallanezhad, David Singhal, Soumye Vega, Luis Cheung, Katherine Pawelec, Krzysztof Evans, Michael Luna, Katherine Lou, Jie Galinkin, Erick Hazare, Akshay Purandare, Kaustubh Guan, Ann Warno, Anna Cui, Chen Suhara, Yoshi Likhite, Shibani Mard, Seph Price, Meredith Sleiman, Laya Kaji, Saori Karpas, Udi Briski, Kari Conway, Joey Lightstone, Michael Kautz, Jan Shoeybi, Mohammad Patwary, Mostofa Cohen, Jonathen Kuchaiev, Oleksii Tao, Andrew Catanzaro, Bryan Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, datasets, and training recipes. Nemotron Nano V2 VL builds on Nemotron Nano V2, a hybrid Mamba-Transformer LLM, and innovative token reduction techniques to achieve higher inference throughput in long document and video scenarios. We are releasing model checkpoints in BF16, FP8, and FP4 formats and sharing large parts of our datasets, recipes and training code.
title	NVIDIA Nemotron Nano V2 VL
topic	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2511.03929

Similar Items