Следене
Bharat Venkitesh
Bharat Venkitesh
Machine Learning at Cohere
Потвърден имейл адрес: cohere.ai
Заглавие
Позовавания
Позовавания
Година
Snapkv: Llm knows what you are looking for before generation
Y Li, Y Huang, B Yang, B Venkitesh, A Locatelli, H Ye, T Cai, P Lewis, ...
arXiv preprint arXiv:2404.14469, 2024
772024
Aya 23: Open weight releases to further multilingual progress
V Aryabumi, J Dang, D Talupuru, S Dash, D Cairuz, H Lin, B Venkitesh, ...
arXiv preprint arXiv:2405.15032, 2024
612024
Intriguing properties of quantization at scale
A Ahmadian, S Dash, H Chen, B Venkitesh, ZS Gou, P Blunsom, A Üstün, ...
Advances in Neural Information Processing Systems 36, 34278-34294, 2023
322023
Exploring low rank training of deep neural networks
SR Kamalakara, A Locatelli, B Venkitesh, J Ba, Y Gal, AN Gomez
arXiv preprint arXiv:2209.13569, 2022
192022
Deformable 3D CAD models in mobile augmented reality for tele-assistance
KPK Reddy, B Venkitesh, A Varghese, N Narendra, G Chandra, ...
2015 Asia Pacific Conference on Multimedia and Broadcasting, 1-5, 2015
112015
Fully quantizing a simplified transformer for end-to-end speech recognition
A Bie, B Venkitesh, J Monteiro, MA Haidar, M Rezagholizadeh
arXiv preprint arXiv:1911.03604, 2019
82019
Predicting twitter engagement with deep language models
M Volkovs, Z Cheng, M Ravaut, H Yang, K Shen, JP Zhou, A Wong, ...
Proceedings of the Recommender Systems Challenge 2020, 38-43, 2020
72020
Smart roaming: How operator cooperation can increase spectrum usage efficiency at practically no cost
B Venkitesh, C Rosenberg
IEEE Transactions on Network and Service Management 16 (2), 690-700, 2019
72019
Aya 23: Open weight releases to further multilingual progress, 2024
V Aryabumi, J Dang, D Talupuru, S Dash, D Cairuz, H Lin, B Venkitesh, ...
URL https://arxiv. org/abs/2405.15032, 0
5
Bam! just like that: Simple and efficient parameter upcycling for mixture of experts
Q Zhang, N Gritsch, D Gnaneshwar, S Guo, D Cairuz, B Venkitesh, ...
arXiv preprint arXiv:2408.08274, 2024
32024
Aya expanse: Combining research breakthroughs for a new multilingual frontier
J Dang, S Singh, D D'souza, A Ahmadian, A Salamanca, M Smith, ...
arXiv preprint arXiv:2412.04261, 2024
22024
Rope to Nope and Back Again: A New Hybrid Attention Strategy
B Yang, B Venkitesh, D Talupuru, H Lin, D Cairuz, P Blunsom, A Locatelli
arXiv preprint arXiv:2501.18795, 2025
2025
System and Method for Low Rank Training of Neural Networks
SR Kamalakara, B Venkitesh, AN Gomez, AFN Locatelli
US Patent App. 17/814,041, 2023
2023
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–13