Követés
Yang Zhang
Yang Zhang
E-mail megerősítve itt: comp.nus.edu.sg - Kezdőlap
Cím
Hivatkozott rá
Hivatkozott rá
Év
Fine-grained neural network explanation by identifying input features with predictive information
Y Zhang, A Khakzar, Y Li, A Farshad, ST Kim, N Navab
Advances in Neural Information Processing Systems (NeurIPS) 2021, 2021
312021
Explaining covid-19 and thoracic pathology model predictions by identifying informative input features
A Khakzar, Y Zhang, W Mansour, Y Cai, Y Li, Y Zhang, ST Kim, N Navab
Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021, 2021
182021
The stronger the diffusion model, the easier the backdoor: Data poisoning to induce copyright breaches without adjusting finetuning pipeline
H Wang, Q Shen, Y Tong, Y Zhang, K Kawaguchi
International Conference on Machine Learning (ICML) 2024, 2024
162024
Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
Y Zhang, TT Tzun, LW Hern, T Sim, K Kawaguchi
The European Conference on Computer Vision (ECCV) 2024, 2024
102024
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
Y Zhang, Y Li, X Wang, Q Shen, B Plank, B Bischl, M Rezaei, ...
arXiv preprint arXiv:2405.18218, 2024
42024
Investigating Copyright Issues of Diffusion Models under Practical Scenarios
Y Zhang, TT Tzun, LW Hern, H Wang, K Kawaguchi
ECCV 2024 Workshop The Dark Side of Generative AIs and Beyond, 2023
4*2023
Investigating Layer Importance in Large Language Models
Y Zhang, Y Dong, K Kawaguchi
EMNLP 2024 BlackboxNLP, 2024
22024
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Q Shen, Y Wang, Z Yang, X Li, H Wang, Y Zhang, J Scarlett, Z Zhu, ...
Advances in Neural Information Processing Systems (NeurIPS) 2024, 2024
12024
AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Y Zhang, Y Li, H Brown, M Rezaei, B Bischl, P Torr, A Khakzar, ...
Neurips 2023 Workshop XAIA, 2023
12023
Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models
A Khakzar, Y Li, Y Zhang, M Sanisoglu, ST Kim, M Rezaei, B Bischl, ...
ICML 2022 Workshop on Interpretable Machine Learning in Healthcare, 2022
12022
Effortless Efficiency: Low-Cost Pruning of Diffusion Models
Y Zhang, E Jin, Y Dong, A Khakzar, P Torr, J Stegmaier, K Kawaguchi
arXiv preprint arXiv:2412.02852, 2024
2024
A Dual-Perspective Approach to Evaluating Feature Attribution Methods
Y Li, Y Zhang, K Kawaguchi, A Khakzar, B Bischl, M Rezaei
Transaction on Machine Learning Research, 2023
2023
A rendszer jelenleg nem tudja elvégezni a műveletet. Próbálkozzon újra később.
Cikkek 1–12