Manli Shu

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 22

Top Topics

Document Length

Learning Models

Gradient Direction

Knowledge Transfer

Top Venues

Publications

Yuancheng Xu, Jiarui Yao, Manli Shu, Yanchao Sun, Zichu Wu, Ning Yu, Tom Goldstein, Furong Huang
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models. CoRR (2024)
John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein
On the Reliability of Watermarks for Large Language Models. CoRR (2023)
Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithvijit Chattopadhyay, Mark Ibrahim, Adrien Bardes, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks. CoRR (2023)
Manli Shu, Jiongxiao Wang, Chen Zhu, Jonas Geiping, Chaowei Xiao, Tom Goldstein
On the Exploitability of Instruction Tuning. NeurIPS (2023)
Manli Shu, Jiongxiao Wang, Chen Zhu, Jonas Geiping, Chaowei Xiao, Tom Goldstein
On the Exploitability of Instruction Tuning. CoRR (2023)
Manli Shu, Le Xue, Ning Yu, Roberto Martín-Martín, Juan Carlos Niebles, Caiming Xiong, Ran Xu
Model-Agnostic Hierarchical Attention for 3D Object Detection. CoRR (2023)
Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithvijit Chattopadhyay, Mark Ibrahim, Adrien Bardes, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks. NeurIPS (2023)
Neel Jain, Khalid Saifullah, Yuxin Wen, John Kirchenbauer, Manli Shu, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models. CoRR (2023)
Roman Levin, Manli Shu, Eitan Borgnia, Furong Huang, Micah Goldblum, Tom Goldstein
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability. NeurIPS (2022)
Amin Ghiasi, Hamid Kazemi, Eitan Borgnia, Steven Reich, Manli Shu, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein
What do Vision Transformers Learn? A Visual Exploration. CoRR (2022)
Manli Shu, Weili Nie, De-An Huang, Zhiding Yu, Tom Goldstein, Anima Anandkumar, Chaowei Xiao
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models. CoRR (2022)
Renkun Ni, Manli Shu, Hossein Souri, Micah Goldblum, Tom Goldstein
The Close Relationship Between Contrastive Learning and Meta-Learning. ICLR (2022)
Manli Shu, Weili Nie, De-An Huang, Zhiding Yu, Tom Goldstein, Anima Anandkumar, Chaowei Xiao
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models. NeurIPS (2022)
Manli Shu, Yu Shen, Ming C. Lin, Tom Goldstein
Adversarial Differentiable Data Augmentation for Autonomous Systems. ICRA (2021)
Yu Shen, Laura Y. Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming C. Lin
Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images. CoRR (2021)
Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein
Encoding Robustness to Image Style via Adversarial Feature Perturbations. NeurIPS (2021)
Yu Shen, Laura Y. Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming C. Lin
Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering. NeurIPS (2021)
Roman Levin, Manli Shu, Eitan Borgnia, Furong Huang, Micah Goldblum, Tom Goldstein
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability. CoRR (2021)
Ahmed Abdelkader, Michael J. Curry, Liam Fowl, Tom Goldstein, Avi Schwarzschild, Manli Shu, Christoph Studer, Chen Zhu
Headless Horseman: Adversarial Attacks on Transfer Learning Models. ICASSP (2020)
Chen Zhu, Zheng Xu, Ali Shafahi, Manli Shu, Amin Ghiasi, Tom Goldstein
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer. CoRR (2020)
Ahmed Abdelkader, Michael J. Curry, Liam Fowl, Tom Goldstein, Avi Schwarzschild, Manli Shu, Christoph Studer, Chen Zhu
Headless Horseman: Adversarial Attacks on Transfer Learning Models. CoRR (2020)
Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein
Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization. CoRR (2020)