18 citations · 39 across the 6 of their papers we have counts for
6 papers
MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing
Nianwen Si, Hao Zhang, Weiqiang Zhang
Large language models are known for encoding a vast amount of factual knowledge, but they often becomes outdated due to the ever-changing nature of external information. A promisin…
Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges
Nianwen Si, Hao Zhang, Heyu Chang +3
In recent years, large language models (LLMs) have spurred a new research paradigm in natural language processing. Despite their excellent capability in knowledge-based question an…
Tuning Large language model for End-to-end Speech Translation
Hao Zhang, Nianwen Si, Yaqi Chen +4
With the emergence of large language models (LLMs), multimodal models based on LLMs have demonstrated significant potential. Models such as LLaSM, X-LLM, and SpeechGPT exhibit an i…
DropDim: A Regularization Method for Transformer Networks
Hao Zhang, Dan Qu, Keji Shao +1
We introduceDropDim, a structured dropout method designed for regularizing the self-attention mechanism, which is a key component of the transformer. In contrast to the general dro…
Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning
Hao Zhang, Nianwen Si, Yaqi Chen +4
The end-to-end speech translation (E2E-ST) model has gradually become a mainstream paradigm due to its low latency and less error propagation. However, it is non-trivial to train s…
Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation
Hao Zhang, Nianwen Si, Yaqi Chen +4
Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often r…