| Reducing gender bias in word-level language models with a gender-equalizing loss function Y Qian, U Muaz, B Zhang, JW Hyun Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019 | 116 | 2019 |
| How easy is it to fool your multimodal llms? an empirical analysis on deceptive prompts Y Qian, H Zhang, Y Yang, Z Gan NeurIPS 2024 Safe Generative AI Workshop, 2024 | 26 | 2024 |
| Mia-bench: Towards better instruction following evaluation of multimodal llms Y Qian, H Ye, JP Fauconnier, P Grasch, Y Yang, Z Gan International Conference on Learning Representations (ICLR2025), 2025 | 12 | 2025 |
| Gender stereotypes differ between male and female writings Y Qian Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019 | 8 | 2019 |
| Understanding alignment in multimodal llms: A comprehensive study E Amirloo, JP Fauconnier, C Roesmann, C Kerl, R Boney, Y Qian, Z Wang, ... arXiv preprint arXiv:2407.02477, 2024 | 7 | 2024 |
| Story-level Text Style Transfer: A Proposal Y Qian Proceedings of the 58th Annual Meeting of the Association for Computational …, 2020 | 2 | 2020 |
Zhe GanResearch Scientist, AppleVerified email at apple.com