Xin Zhang

Han Zhu, Wei Kang, Liyong Guo et al.

Generating spoken dialogue is more challenging than monologue text-to-speech (TTS) due to the need for realistic turn-taking and distinct speaker timbres. Existing spoken dialogue generation models, being auto-regressive, suffer from slow and unstable inference. To overcome these limitations, we introduce ZipVoice-Dialog, a non-autoregressive zero-shot spoken dialogue generation model built upon flow matching. Key designs include: 1) speaker-turn embeddings for precise speaker turn-taking; 2) a curriculum learning strategy for stable speech-text alignment; 3) specialized strategies to enable stereo dialogue generation. Additionally, recognizing the lack of open-source large-scale spoken dialogue datasets, we curated OpenDialog, a 6.8k-hour spoken dialogue dataset from in-the-wild speech data. Furthermore, we established a benchmark to comprehensively evaluate various models. Experimental results demonstrate that ZipVoice-Dialog achieves superior performance in intelligibility, speaker turn-taking accuracy, speaker similarity, and inference speed. Our codes, model checkpoints, demo samples, and the OpenDialog dataset are all publicly available at https://github.com/k2-fsa/ZipVoice.

Xin Zhang, Victor S. Sheng

Explainability is an essential reason limiting the application of neural networks in many vital fields. Although neuro-symbolic AI hopes to enhance the overall explainability by leveraging the transparency of symbolic learning, the results are less evident than imagined. This article proposes a classification for explainability by considering both model design and behavior of 191 studies from 2013, focusing on neuro-symbolic AI, hoping to inspire scholars who want to understand the explainability of neuro-symbolic AI. Precisely, we classify them into five categories by considering whether the form of bridging the representation differences is readable as their design factor, if there are representation differences between neural networks and symbolic logic learning, and whether a model decision or prediction process is understandable as their behavior factor: implicit intermediate representations and implicit prediction, partially explicit intermediate representations and partially explicit prediction, explicit intermediate representations or explicit prediction, explicit intermediate representation and explicit prediction, unified representation and explicit prediction. We also analyzed the research trends and three significant challenges: unified representations, explainability and transparency, and sufficient cooperation from neural networks and symbolic learning. Finally, we put forward suggestions for future research in three aspects: unified representations, enhancing model explainability, ethical considerations, and social impact.

Xin Zhang, Victor S. Sheng

We propose an innovative token representation and update method in a new ultra-small language model: the Wave network. Specifically, we use a complex vector to represent each token, encoding both global and local semantics of the input text. A complex vector consists of two components: a magnitude vector representing the global semantics of the input text, and a phase vector capturing the relationships between individual tokens and global semantics. Experiments on the AG News text classification task demonstrate that, when generating complex vectors from randomly initialized token embeddings, our single-layer Wave Network achieves 90.91% accuracy with wave interference and 91.66% with wave modulation - outperforming a single Transformer layer using BERT pre-trained embeddings by 19.23% and 19.98%, respectively, and approaching the accuracy of the pre-trained and fine-tuned BERT base model (94.64%). Additionally, compared to BERT base, the Wave Network reduces video memory usage and training time by 77.34% and 85.62% during wave modulation. In summary, we used a 2.4-million-parameter small language model to achieve accuracy comparable to a 100-million-parameter BERT model in text classification.

Weilong Yan, Xin Zhang, Robby T. Tan

Monocular depth estimation under adverse weather conditions (e.g.\ rain, fog, snow, and nighttime) remains highly challenging due to the lack of reliable ground truth and the difficulty of learning from unlabeled real-world data. Existing methods often rely on synthetic adverse data with pseudo-labels, which suffer from domain gaps, or employ self-supervised learning, which violates photometric assumptions in adverse scenarios. In this work, we propose to achieve weather-generalized depth estimation by Parameter-Efficient Fine-Tuning (PEFT) of Vision Foundation Models (VFMs), using only a small amount of high-visibility (normal) data. While PEFT has shown strong performance in semantic tasks such as segmentation, it remains underexplored for geometry -- centric tasks like depth estimation -- especially in terms of balancing effective adaptation with the preservation of pretrained knowledge. To this end, we introduce the Selecting-Tuning-Maintaining (STM) strategy, which structurally decomposes the pretrained weights of VFMs based on two kinds of effective ranks (entropy-rank and stable-rank). In the tuning phase, we adaptively select the proper rank number as well as the task-aware singular directions for initialization, based on the entropy-rank and full-tuned weight; while in the maintaining stage, we enforce a principal direction regularization based on the stable-rank. This design guarantees flexible task adaptation while preserving the strong generalization capability of the pretrained VFM. Extensive experiments on four real-world benchmarks across diverse weather conditions demonstrate that STM not only outperforms existing PEFT methods and full fine-tuning but also surpasses methods trained with adverse synthetic data, and even the depth foundation model

Xin Zhang, Liangxiu Han, Yue Shi et al.

Diabetic Peripheral Neuropathy (DPN) affects nearly half of diabetes patients, requiring early detection. Corneal Confocal Microscopy (CCM) enables non-invasive diagnosis, but automated methods suffer from inefficient feature extraction, reliance on handcrafted priors, and data limitations. We propose HMSViT, a novel Hierarchical Masked Self-Supervised Vision Transformer (HMSViT) designed for corneal nerve segmentation and DPN diagnosis. Unlike existing methods, HMSViT employs pooling-based hierarchical and dual attention mechanisms with absolute positional encoding, enabling efficient multi-scale feature extraction by capturing fine-grained local details in early layers and integrating global context in deeper layers, all at a lower computational cost. A block-masked self supervised learning framework is designed for the HMSViT that reduces reliance on labelled data, enhancing feature robustness, while a multi-scale decoder is used for segmentation and classification by fusing hierarchical features. Experiments on clinical CCM datasets showed HMSViT achieves state-of-the-art performance, with 61.34% mIoU for nerve segmentation and 70.40% diagnostic accuracy, outperforming leading hierarchical models like the Swin Transformer and HiViT by margins of up to 6.39% in segmentation accuracy while using fewer parameters. Detailed ablation studies further reveal that integrating block-masked SSL with hierarchical multi-scale feature extraction substantially enhances performance compared to conventional supervised training. Overall, these comprehensive experiments confirm that HMSViT delivers excellent, robust, and clinically viable results, demonstrating its potential for scalable deployment in real-world diagnostic applications.

Xin Zhang, Victor S. Sheng

This paper provides an in-depth analysis of Wave Network, a novel token representation method derived from the Wave Network, designed to capture both global and local semantics of input text through wave-inspired complex vectors. In complex vector token representation, each token is represented with a magnitude component, capturing the global semantics of the entire input text, and a phase component, encoding the relationships between individual tokens and the global semantics. Building on prior research that demonstrated the effectiveness of wave-like operations, such as interference and modulation, during forward propagation, this study investigates the convergence behavior, backpropagation characteristics, and embedding independence within the Token2Wave framework. A detailed computational complexity analysis shows that Token2Wave can significantly reduce video memory usage and training time compared to BERT. Gradient comparisons for the [CLS] token, total input text, and classifier parameters further highlight Token2Wave's unique characteristics. This research offers new insights into wave-based token representations, demonstrating their potential to enable efficient and computationally friendly language model architectures.