Follow
Michael Santacroce
Michael Santacroce
Researcher at Microsoft
Verified email at microsoft.com - Homepage
Title
Cited by
Cited by
Year
Phi-2: The surprising power of small language models
M Javaheripi, S Bubeck, M Abdin, J Aneja, S Bubeck, CCT Mendes, ...
Microsoft Research Blog, 2023
37*2023
What matters in the structured pruning of generative language models?
M Santacroce, Z Wen, Y Shen, Y Li
arXiv preprint arXiv:2302.03773, 2023
122023
Efficient computation of deep nonlinear infinite-width neural networks that learn features
G Yang, M Santacroce, EJ Hu
International Conference on Learning Representations, 2021
92021
Efficient rlhf: Reducing the memory usage of ppo
M Santacroce, Y Lu, H Yu, Y Li, Y Shen
arXiv preprint arXiv:2309.00754, 2023
72023
Detecting malicious assembly with deep learning
M Santacroce, D Koranek, D Kapp, A Ralescu, R Jha
NAECON 2018-IEEE National Aerospace and Electronics Conference, 82-85, 2018
72018
Detecting malware code as video with compressed, time-distributed neural networks
ML Santacroce, D Koranek, R Jha
IEEE Access 8, 132748-132760, 2020
52020
Adapting llm agents through communication
K Wang, Y Lu, M Santacroce, Y Gong, C Zhang, Y Shen
arXiv preprint arXiv:2310.01444, 2023
32023
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
M Abdin, SA Jacobs, AA Awan, J Aneja, A Awadallah, H Awadalla, ...
arXiv preprint arXiv:2404.14219, 2024
22024
Direct nash optimization: Teaching language models to self-improve with general preferences
C Rosset, CA Cheng, A Mitra, M Santacroce, A Awadallah, T Xie
arXiv preprint arXiv:2404.03715, 2024
22024
A Foray Into Extracting Malicious Features from Executable Code with Neural Network Salience
M Santacroce, W Stegner, D Koranek, R Jha
2019 IEEE National Aerospace and Electronics Conference (NAECON), 185-191, 2019
12019
Neural Classification of Malware-as-Video with Considerations for In-Hardware Inferencing
ML Santacroce
University of Cincinnati Cincinnati, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–11