Xiaoqing Li

Zhijian Zhuo, Yutao Zeng, Ya Wang et al. · bytedance

Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, challenges remain in training deep transformer networks, especially regarding the position of layer normalization. While Pre-Norm structures facilitate more stable training owing to their stronger identity path, they often lead to suboptimal performance compared to Post-Norm. In this paper, we propose $\textbf{HybridNorm}$, a simple yet effective hybrid normalization strategy that integrates the advantages of both Pre-Norm and Post-Norm. Specifically, HybridNorm employs QKV normalization within the attention mechanism and Post-Norm in the feed-forward network (FFN) of each transformer block. We provide both theoretical insights and empirical evidence demonstrating that HybridNorm improves gradient flow and model robustness. Extensive experiments on large-scale transformer models, including both dense and sparse variants, show that HybridNorm consistently outperforms both Pre-Norm and Post-Norm approaches across multiple benchmarks. These findings highlight the potential of HybridNorm as a more stable and effective technique for improving the training and performance of deep transformer models. Code is available at https://github.com/BryceZhuo/HybridNorm.

Yan Zhang, Peng Gao, Xiao-Qing Li

The Ray-Casting algorithm is an important method for fast real-time surface display from 3D medical images. Based on the Ray-Casting algorithm, a novel parallel Ray-Casting algorithm is proposed in this paper. A novel operation is introduced and defined as a star operation, and star operations can be computed in parallel in the proposed algorithm compared with the serial chain of star operations in the Ray-Casting algorithm. The computation complexity of the proposed algorithm is reduced from $O(n)$ to $O(\log^n_2)$.

Xiaoqing Li, Jiajun Zhang, Chengqing Zong

Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus and the fixed network is used to translate all the test sentences. We argue that the general fixed network cannot best fit the specific test sentences. In this paper, we propose the dynamic NMT which learns a general network as usual, and then fine-tunes the network for each test sentence. The fine-tune work is done on a small set of the bilingual training data that is obtained through similarity search according to the test sentence. Extensive experiments demonstrate that this method can significantly improve the translation performance, especially when highly similar sentences are available.

Xiaoqing Li, Jiajun Zhang, Chengqing Zong

In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol. Previous solution (Luong et al., 2015) resorts to use multiple numbered unks to learn the correspondence between source and target rare words. However, testing words unseen in the training corpus cannot be handled by this method. And it also suffers from the noisy word alignment. In this paper, we focus on a major type of rare words -- named entity (NE), and propose to translate them with character level sequence to sequence model. The NE translation model is further used to derive high quality NE alignment in the bilingual training corpus. With the integration of NE translation and alignment modules, our NMT system is able to surpass the baseline system by 2.9 BLEU points on the Chinese to English task.