| M-adapter: Modality adaptation for end-to-end speech-to-text translation J Zhao, H Yang, E Shareghi, G Haffari Interspeech 2022, 2022 | 19 | 2022 |
| Investigating pre-trained audio encoders in the low-resource condition H Yang, J Zhao, G Haffari, E Shareghi Interspeech 2023, 2023 | 5 | 2023 |
| Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models H Yang, L Qu, E Shareghi, G Haffari NAACL 2025, 2024 | 2 | 2024 |
| Self-supervised rewiring of pre-trained speech encoders: Towards faster fine-tuning with less labels in speech processing H Yang, J Zhao, G Haffari, E Shareghi EMNLP 2022-Findings, 2022 | 2 | 2022 |
| Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models H Yang, L Qu, E Shareghi, G Haffari arXiv preprint arXiv:2410.11459, 2024 | 1 | 2024 |
| RedApt: An Adaptor for wav2vec 2 Encoding\\Faster and Smaller Speech Translation without Quality Compromise J Zhao, H Yang, G Haffari, E Shareghi EMNLP 2022-Findings, 2022 | 1 | 2022 |
| Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights H Yang, L Qu, E Shareghi, G Haffari EMNLP 2024, 2024 | | 2024 |
| Double Mixture: Towards Continual Event Detection from Speech J Kang, T Wu, J Zhao, G Wang, Y Wei, H Yang, G Qi, YF Li, G Haffari arXiv preprint arXiv:2404.13289, 2024 | | 2024 |
