Follow
Mingjie Sun
Mingjie Sun
Verified email at cs.cmu.edu - Homepage
Title
Cited by
Cited by
Year
Rethinking the Value of Network Pruning
Z Liu*, M Sun*, T Zhou, G Huang, T Darrell
International Conference on Learning Representations (ICLR) 2019, 2019
17372019
A Simple and Effective Pruning Approach for Large Language Models
M Sun*, Z Liu*, A Bair, JZ Kolter
International Conference on Learning Representations (ICLR), 2024
2562024
Denoised Smoothing: A Provable Defense for Pretrained Classifiers
H Salman, M Sun, G Yang, A Kapoor, JZ Kolter
Advances in Neural Information Processing Systems 33, 21945-21957, 2020
1622020
Data poisoning attack against unsupervised node embedding methods
M Sun, J Tang, H Li, B Li, C Xiao, Y Chen, D Song
arXiv preprint arXiv:1810.12881, 2018
842018
Characterizing attacks on deep reinforcement learning
X Pan, C Xiao, W He, S Yang, J Peng, M Sun, J Yi, Z Yang, M Liu, B Li, ...
arXiv preprint arXiv:1907.09470, 2019
782019
Test-Time Adaptation via Conjugate Pseudo-Labels
S Goyal*, M Sun*, A Raghunathan, JZ Kolter
Advances in Neural Information Processing Systems (NeurIPS) 2022, 2022
762022
Massive Activations in Large Language Models
M Sun, X Chen, JZ Kolter, Z Liu
Conference on Language Modeling (COLM), 2024, 2024
262024
Can shape structure features improve model robustness under diverse adversarial settings?
M Sun, Z Li, C Xiao, H Qiu, B Kailkhura, M Liu, B Li
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
242021
Poisoned classifiers are not only backdoored, they are fundamentally broken
M Sun, S Agarwal, JZ Kolter
arXiv preprint arXiv:2010.09080, 2020
222020
(Certified!!) Adversarial Robustness for Free!
N Carlini, F Tramer, K Dj Dvijotham, L Rice, M Sun, JZ Kolter
International Conference on Learning Representations (ICLR), 2023
122023
Beyond size: How gradients shape pruning decisions in large language models
RJ Das, M Sun, L Ma, Z Shen
arXiv preprint arXiv:2311.04902, 2023
92023
Method and system for breaking backdoored classifiers through adversarial examples
SUN Mingjie, J Kolter, FJC CONDESSA
US Patent App. 17/035,173, 2022
82022
Single Image Backdoor Inversion via Robust Smoothed Classifiers
M Sun, JZ Kolter
Computer Vision and Pattern Recognition (CVPR) 2023, 2023
72023
Reliable Test-Time Adaptation via Agreement-on-the-Line
E Kim, M Sun, A Raghunathan, Z Kolter
arXiv preprint arXiv:2310.04941, 2023
32023
System and method for test-time adaptation via conjugate pseudolabels
SUN Mingjie, S Goyal, A Raghunathan, J Kolter, WY Lin
US Patent App. 17/868,267, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–15