Obserwuj
Krishnateja Killamsetty
Krishnateja Killamsetty
Research Scientist, IBM Research
Zweryfikowany adres z ibm.com - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Grad-match: Gradient matching based data subset selection for efficient deep model training
K Killamsetty, S Durga, G Ramakrishnan, A De, R Iyer
International Conference on Machine Learning, 5464-5474, 2021
2502021
Glister: Generalization based data subset selection for efficient and robust learning
K Killamsetty, D Sivasubramanian, G Ramakrishnan, R Iyer
Proceedings of the AAAI Conference on Artificial Intelligence 35 (9), 8110-8118, 2021
2462021
Gcr: Gradient coreset based replay buffer selection for continual learning
R Tiwari, K Killamsetty, R Iyer, P Shenoy
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
1482022
Similar: Submodular information measures based active learning in realistic scenarios
S Kothawade, N Beck, K Killamsetty, R Iyer
Advances in Neural Information Processing Systems 34, 18685-18697, 2021
1122021
Retrieve: Coreset selection for efficient and robust semi-supervised learning
K Killamsetty, X Zhao, F Chen, R Iyer
Advances in neural information processing systems 34, 14488-14501, 2021
962021
A nested bi-level optimization framework for robust few shot learning
K Killamsetty, C Li, C Zhao, F Chen, R Iyer
Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7176-7184, 2022
27*2022
Semi-supervised data programming with subset selection
A Maheshwari, O Chatterjee, K Killamsetty, G Ramakrishnan, R Iyer
arXiv preprint arXiv:2008.09887, 2020
27*2020
How Out-of-Distribution Data Hurts Semi-Supervised Learning
X Zhao, K Krishnateja, R Iyer, F Chen
IEEE International Conference On Data Mining (ICDM) 22, 763-772, 2022
24*2022
Automata: Gradient based data subset selection for compute-efficient hyper-parameter tuning
K Killamsetty, GS Abhishek, A Lnu, G Ramakrishnan, A Evfimievski, ...
Advances in Neural Information Processing Systems 35, 28721-28733, 2022
232022
Learning to robustly aggregate labeling functions for semi-supervised data programming
A Maheshwari, K Killamsetty, G Ramakrishnan, R Iyer, M Danilevsky, ...
arXiv preprint arXiv:2109.11410, 2021
182021
Orient: Submodular mutual information measures for data subset selection under distribution shift
A Karanam, K Killamsetty, H Kokel, R Iyer
Advances in neural information processing systems 35, 31796-31808, 2022
112022
MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning
K Killamsetty, AV Evfimievski, T Pedapati, K Kate, L Popa, R Iyer
arXiv preprint arXiv:2301.13287, 2023
8*2023
A data subset selection framework for efficient hyper-parameter tuning and automatic machine learning
S Visalpara, K Killamsetty, R Iyer
ICML Workshops, 182, 2021
72021
Beyond active learning: Leveraging the full potential of human interaction via auto-labeling, human correction, and human verification
N Beck, K Killamsetty, S Kothawade, R Iyer
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024
62024
INGENIOUS: Using informative data subsets for efficient pre-training of language models
HK Renduchintala, K Killamsetty, S Bhatia, M Aggarwal, G Ramakrishnan, ...
Findings of the Association for Computational Linguistics: EMNLP 2023, 6690-6705, 2023
52023
SCoRe: Submodular Combinatorial Representation Learning for Real-World Class-Imbalanced Settings
A Majee, S Kothawade, K Killamsetty, R Iyer
In Forty-First International Conference on Machine Learning ICML 2024, 2024
3*2024
Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
A Pareja, NS Nayak, H Wang, K Killamsetty, S Sudalairaj, W Zhao, S Han, ...
arXiv preprint arXiv:2412.13337, 2024
22024
DELIFT: Data Efficient Language model Instruction Fine Tuning
I Agarwal, K Killamsetty, L Popa, M Danilevksy
arXiv preprint arXiv:2411.04425, 2024
22024
Data Subset Selection for Compute Efficient Deep Learning
K Killamsetty, R Iyer, G Ramakrishnan, V Gogate, S Natarajan
University of Texas at Dallas, 2023
2023
Training Mice to Compete with Elephants: A Guide for Customizing Small-Sized LLMs on Knowledge and Skills Data
A Pareja, NS Nayak, H Wang, K Killamsetty, S Sudalairaj, W Zhao, S Han, ...
The Thirteenth International Conference on Learning Representations, 0
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20