Huizhi Liang

Zhenyu Liu, Haoran Duan, Huizhi Liang et al.

Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that limit their performance: (1) Previous methods primarily use static ground truth for adversarial training, but this often causes robust overfitting; (2) The loss functions are either Mean Squared Error or KL-divergence leading to a sub-optimal performance on clean accuracy. To solve those problems, we propose a dynamic label adversarial training (DYNAT) algorithm that enables the target model to gradually and dynamically gain robustness from the guide model's decisions. Additionally, we found that a budgeted dimension of inner optimization for the target model may contribute to the trade-off between clean accuracy and robust accuracy. Therefore, we propose a novel inner optimization method to be incorporated into the adversarial training. This will enable the target model to adaptively search for adversarial examples based on dynamic labels from the guiding model, contributing to the robustness of the target model. Extensive experiments validate the superior performance of our approach.

Tong Wu, Thanet Markchom, Huizhi Liang

Word sense plausibility rating requires predicting the human-perceived plausibility of a given word sense on a 1-5 scale in the context of short narrative stories containing ambiguous homonyms. This paper systematically compares three approaches: (1) embedding-based methods pairing sentence embeddings with standard regressors, (2) transformer fine-tuning with parameter-efficient adaptation, and (3) large language model (LLM) prompting with structured reasoning and explicit decision rules. The best-performing system employs a structured prompting strategy that decomposes evaluation into narrative components (precontext, target sentence, ending) and applies explicit decision rules for rating calibration. The analysis reveals that structured prompting with decision rules outperforms both fine-tuned models and embedding-based approaches, and that prompt design matters more than model scale for this task.

Ziwei Zheng, Huizhi Liang, Vaclav Snasel et al.

We scrutinize the structural and operational aspects of deep learning models, particularly focusing on the nuances of learnable parameters (weight) statistics, distribution, node interaction, and visualization. By establishing correlations between variance in weight patterns and overall network performance, we investigate the varying (optimal and suboptimal) performances of various deep-learning models. Our empirical analysis extends across widely recognized datasets such as MNIST, Fashion-MNIST, and CIFAR-10, and various deep learning models such as deep neural networks (DNNs), convolutional neural networks (CNNs), and vision transformer (ViT), enabling us to pinpoint characteristics of learnable parameters that correlate with successful networks. Through extensive experiments on the diverse architectures of deep learning models, we shed light on the critical factors that influence the functionality and efficiency of DNNs. Our findings reveal that successful networks, irrespective of datasets or models, are invariably similar to other successful networks in their converged weights statistics and distribution, while poor-performing networks vary in their weights. In addition, our research shows that the learnable parameters of widely varied deep learning models such as DNN, CNN, and ViT exhibit similar learning characteristics.

Haonan Zhang, Dongxia Wang, Zhu Sun et al.

Recommender systems (RSs) are designed to provide personalized recommendations to users. Recently, knowledge graphs (KGs) have been widely introduced in RSs to improve recommendation accuracy. In this study, however, we demonstrate that RSs do not necessarily perform worse even if the KG is downgraded to the user-item interaction graph only (or removed). We propose an evaluation framework KG4RecEval to systematically evaluate how much a KG contributes to the recommendation accuracy of a KG-based RS, using our defined metric KGER (KG utilization efficiency in recommendation). We consider the scenarios where knowledge in a KG gets completely removed, randomly distorted and decreased, and also where recommendations are for cold-start users. Our extensive experiments on four commonly used datasets and a number of state-of-the-art KG-based RSs reveal that: to remove, randomly distort or decrease knowledge does not necessarily decrease recommendation accuracy, even for cold-start users. These findings inspire us to rethink how to better utilize knowledge from existing KGs, whereby we discuss and provide insights into what characteristics of datasets and KG-based RSs may help improve KG utilization efficiency. The code and supplementary material of this paper are available at: https://github.com/HotBento/KG4RecEval.

Nicolay Rusnachenko, Huizhi Liang

Emotion expression is one of the essential traits of conversations. It may be self-related or caused by another speaker. The variety of reasons may serve as a source of the further emotion causes: conversation history, speaker's emotional state, etc. Inspired by the most recent advances in Chain-of-Thought, in this work, we exploit the existing three-hop reasoning approach (THOR) to perform large language model instruction-tuning for answering: emotion states (THOR-state), and emotion caused by one speaker to the other (THOR-cause). We equip THOR-cause with the reasoning revision (rr) for devising a reasoning path in fine-tuning. In particular, we rely on the annotated speaker emotion states to revise reasoning path. Our final submission, based on Flan-T5-base (250M) and the rule-based span correction technique, preliminary tuned with THOR-state and fine-tuned with THOR-cause-rr on competition training data, results in 3rd and 4th places (F1-proportional) and 5th place (F1-strict) among 15 participating teams. Our THOR implementation fork is publicly available: https://github.com/nicolay-r/THOR-ECAC

Thanet Markchom, Huizhi Liang, James Ferryman

Explainability of recommender systems has become essential to ensure users' trust and satisfaction. Various types of explainable recommender systems have been proposed including explainable graph-based recommender systems. This review paper discusses state-of-the-art approaches of these systems and categorizes them based on three aspects: learning methods, explaining methods, and explanation types. It also explores the commonly used datasets, explainability evaluation methods, and future directions of this research area. Compared with the existing review papers, this paper focuses on explainability based on graphs and covers the topics required for developing novel explainable graph-based recommender systems.

Zhiyuan Feng, Zhaolu Kang, Qijie Wang et al.

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of VLMs focus on single-view settings, leaving their ability to integrate multi-view information underexplored. At the same time, multi-camera setups are increasingly standard in robotic platforms, as they provide complementary perspectives to mitigate occlusion and depth ambiguity. Whether VLMs can effectively leverage such multi-view inputs for robotic reasoning therefore remains an open question. To bridge this gap, we introduce MV-RoboBench, a benchmark specifically designed to evaluate the multi-view spatial reasoning capabilities of VLMs in robotic manipulation. MV-RoboBench consists of 1.7k manually curated QA items across eight subtasks, divided into two primary categories: spatial understanding and robotic execution. We evaluate a diverse set of existing VLMs, including both open-source and closed-source models, along with enhanced versions incorporating CoT-inspired techniques. The results show that state-of-the-art models remain far below human performance, underscoring the substantial challenges VLMs face in multi-view robotic perception. Additionally, our analysis uncovers two key findings: (i) spatial intelligence and robotic task execution are positively correlated in multi-view robotic scenarios; and (ii) strong performance on existing general-purpose single-view spatial understanding benchmarks does not reliably translate to success in the robotic spatial tasks assessed by our benchmark. We release MV-RoboBench as an open resource to foster progress in spatially grounded VLMs and VLAs, providing not only data but also a standardized evaluation protocol for multi-view embodied reasoning.

Feng Xiong, Thanet Markchom, Ziwei Zheng et al.

SemEval-2024 Task 8 introduces the challenge of identifying machine-generated texts from diverse Large Language Models (LLMs) in various languages and domains. The task comprises three subtasks: binary classification in monolingual and multilingual (Subtask A), multi-class classification (Subtask B), and mixed text detection (Subtask C). This paper focuses on Subtask A & B. Each subtask is supported by three datasets for training, development, and testing. To tackle this task, two methods: 1) using traditional machine learning (ML) with natural language preprocessing (NLP) for feature extraction, and 2) fine-tuning LLMs for text classification. The results show that transformer models, particularly LoRA-RoBERTa, exceed traditional ML methods in effectiveness, with majority voting being particularly effective in multilingual contexts for identifying machine-generated texts.

Qixiu Li, Yu Deng, Yaobo Liang et al.

This paper presents a novel approach for pretraining robotic manipulation Vision-Language-Action (VLA) models using a large corpus of unscripted real-life video recordings of human hand activities. Treating human hand as dexterous robot end-effector, we show that "in-the-wild" egocentric human videos without any annotations can be transformed into data formats fully aligned with existing robotic V-L-A training data in terms of task granularity and labels. This is achieved by the development of a fully-automated holistic human activity analysis approach for arbitrary human hand videos. This approach can generate atomic-level hand activity segments and their language descriptions, each accompanied with framewise 3D hand motion and camera motion. We process a large volume of egocentric videos and create a hand-VLA training dataset containing 1M episodes and 26M frames. This training data covers a wide range of objects and concepts, dexterous manipulation tasks, and environment variations in real life, vastly exceeding the coverage of existing robot data. We design a dexterous hand VLA model architecture and pretrain the model on this dataset. The model exhibits strong zero-shot capabilities on completely unseen real-world observations. Additionally, fine-tuning it on a small amount of real robot action data significantly improves task success rates and generalization to novel objects in real robotic experiments. We also demonstrate the appealing scaling behavior of the model's task performance with respect to pretraining data scale. We believe this work lays a solid foundation for scalable VLA pretraining, advancing robots toward truly generalizable embodied intelligence.

Tian Li, Yujian Sun, Huizhi Liang

The SemEval-2025 Task 11, Bridging the Gap in Text-Based Emotion Detection, introduces an emotion recognition challenge spanning over 28 languages. This competition encourages researchers to explore more advanced approaches to address the challenges posed by the diversity of emotional expressions and background variations. It features two tracks: multi-label classification (Track A) and emotion intensity prediction (Track B), covering six emotion categories: anger, fear, joy, sadness, surprise, and disgust. In our work, we systematically explore the benefits of two contrastive learning approaches: sample-based (Contrastive Reasoning Calibration) and generation-based (DPO, SimPO) contrastive learning. The sample-based contrastive approach trains the model by comparing two samples to generate more reliable predictions. The generation-based contrastive approach trains the model to differentiate between correct and incorrect generations, refining its prediction. All models are fine-tuned from LLaMa3-Instruct-8B. Our system achieves 9th place in Track A and 6th place in Track B for English, while ranking among the top-tier performing systems for other languages.

Zhenyu Liu, Huizhi Liang, Rajiv Ranjan et al.

The robustness of Deep Neural Network models is crucial for defending models against adversarial attacks. Recent defense methods have employed collaborative learning frameworks to enhance model robustness. Two key limitations of existing methods are (i) insufficient guidance of the target model via loss functions and (ii) non-collaborative adversarial generation. We, therefore, propose a dual regularization loss (D2R Loss) method and a collaborative adversarial generation (CAG) strategy for adversarial training. D2R loss includes two optimization steps. The adversarial distribution and clean distribution optimizations enhance the target model's robustness by leveraging the strengths of different loss functions obtained via a suitable function space exploration to focus more precisely on the target model's distribution. CAG generates adversarial samples using a gradient-based collaboration between guidance and target models. We conducted extensive experiments on three benchmark databases, including CIFAR-10, CIFAR-100, Tiny ImageNet, and two popular target models, WideResNet34-10 and PreActResNet18. Our results show that D2R loss with CAG produces highly robust models.

Jiaying Hong, Thanet Markchom, Jianfei Xu et al.

SemEval-2025 Task 3 (Mu-SHROOM) focuses on detecting hallucinations in content generated by various large language models (LLMs) across multiple languages. This task involves not only identifying the presence of hallucinations but also pinpointing their specific occurrences. To tackle this challenge, this study introduces two methods: modified RefChecker and modified SelfCheckGPT. The modified RefChecker integrates prompt-based factual verification into References, structuring them as claim-based tests rather than single external knowledge sources. The modified SelfCheckGPT incorporates external knowledge to overcome its reliance on internal knowledge. In addition, both methods' original prompt designs are enhanced to identify hallucinated words within LLM-generated texts. Experimental results demonstrate the effectiveness of the approach, achieving a high ranking on the test dataset in detecting hallucinations across various languages, with an average IoU of 0.5310 and an average COR of 0.5669.

Ting Zhu, Shufei Duan, Huizhi Liang et al.

The lack of an available emotion pathology database is one of the key obstacles in studying the emotion expression status of patients with dysarthria. The first Chinese multimodal emotional pathological speech database containing multi-perspective information is constructed in this paper. It includes 29 controls and 39 patients with different degrees of motor dysarthria, expressing happy, sad, angry and neutral emotions. All emotional speech was labeled for intelligibility, types and discrete dimensional emotions by developed WeChat mini-program. The subjective analysis justifies from emotion discrimination accuracy, speech intelligibility, valence-arousal spatial distribution, and correlation between SCL-90 and disease severity. The automatic recognition tested on speech and glottal data, with average accuracy of 78% for controls and 60% for patients in audio, while 51% for controls and 38% for patients in glottal data, indicating an influence of the disease on emotional expression.

Pengzhen Xie, Huizhi Liang

Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the generated results often lack controllable academic context and traceable inspiration pathways. To bridge this gap, this paper proposes a scientific idea generation system called GYWI, which combines author knowledge graphs with retrieval-augmented generation (RAG) to form an external knowledge base to provide controllable context and trace of inspiration path for LLMs to generate new scientific ideas. We first propose an author-centered knowledge graph construction method and inspiration source sampling algorithms to construct external knowledge base. Then, we propose a hybrid retrieval mechanism that is composed of both RAG and GraphRAG to retrieve content with both depth and breadth knowledge. It forms a hybrid context. Thirdly, we propose a Prompt optimization strategy incorporating reinforcement learning principles to automatically guide LLMs optimizing the results based on the hybrid context. To evaluate the proposed approaches, we constructed an evaluation dataset based on arXiv (2018-2023). This paper also develops a comprehensive evaluation method including empirical automatic assessment in multiple-choice question task, LLM-based scoring, human evaluation, and semantic space visualization analysis. The generated ideas are evaluated from the following five dimensions: novelty, feasibility, clarity, relevance, and significance. We conducted experiments on different LLMs including GPT-4o, DeepSeek-V3, Qwen3-8B, and Gemini 2.5. Experimental results show that GYWI significantly outperforms mainstream LLMs in multiple metrics such as novelty, reliability, and relevance.

Jiaying Hong, Ting Zhu, Thanet Markchom et al.

With the rise of AI-generated content (AIGC), generating perceptually natural and feeling-aligned music from multimodal inputs has become a central challenge. Existing approaches often rely on explicit emotion labels that require costly annotation, underscoring the need for more flexible feeling-aligned methods. To support multimodal music generation, we construct ArtiCaps, a pseudo feeling-aligned image-music-text dataset created by semantically matching descriptions from ArtEmis and MusicCaps. We further propose Art2Music, a lightweight cross-modal framework that synthesizes music from artistic images and user comments. In the first stage, images and text are encoded with OpenCLIP and fused using a gated residual module; the fused representation is decoded by a bidirectional LSTM into Mel-spectrograms with a frequency-weighted L1 loss to enhance high-frequency fidelity. In the second stage, a fine-tuned HiFi-GAN vocoder reconstructs high-quality audio waveforms. Experiments on ArtiCaps show clear improvements in Mel-Cepstral Distortion, Frechet Audio Distance, Log-Spectral Distance, and cosine similarity. A small LLM-based rating study further verifies consistent cross-modal feeling alignment and offers interpretable explanations of matches and mismatches across modalities. These results demonstrate improved perceptual naturalness, spectral fidelity, and semantic consistency. Art2Music also maintains robust performance with only 50k training samples, providing a scalable solution for feeling-aligned creative audio generation in interactive art, personalized soundscapes, and digital art exhibitions.

Raghda Zahran, Jianfei Xu, Huizhi Liang et al.

Objective This study is part of a series of initiatives at a UK university designed to cultivate a deep understanding of students' perspectives on analytics that resonate with their unique learning needs. It explores collaborative data processing undertaken by postgraduate students who examined an Open University Learning Analytics Dataset (OULAD). Methods A qualitative approach was adopted, integrating a Retrieval-Augmented Generation (RAG) and a Large Language Model (LLM) technique with human-led content analysis to gather information about students' perspectives based on their submitted work. The study involved 72 postgraduate students in 12 groups. Findings The analysis of group work revealed diverse insights into essential learning analytics from the students' perspectives. All groups adopted a structured data science methodology. The questions formulated by the groups were categorised into seven themes, reflecting their specific areas of interest. While there was variation in the selected variables to interpret correlations, a consensus was found regarding the general results. Conclusion A significant outcome of this study is that students specialising in data science exhibited a deeper understanding of learning analytics, effectively articulating their interests through inferences drawn from their analyses. While human-led content analysis provided a general understanding of students' perspectives, the LLM offered nuanced insights.

Jianfei Xu, Thanet Markchom, Huizhi Liang

The complexity of stacked imaging and the massive number of radiographs make writing radiology reports complex and inefficient. Even highly experienced radiologists struggle to maintain accuracy and consistency in interpreting radiographs under prolonged high-intensity work. To address these issues, this work proposes the CRRG-CLIP Model (Chest Radiology Report Generation and Radiograph Classification Model), an end-to-end model for automated report generation and radiograph classification. The model consists of two modules: the radiology report generation module and the radiograph classification module. The generation module uses Faster R-CNN to identify anatomical regions in radiographs, a binary classifier to select key regions, and GPT-2 to generate semantically coherent reports. The classification module uses the unsupervised Contrastive Language Image Pretraining (CLIP) model, addressing the challenges of high-cost labelled datasets and insufficient features. The results show that the generation module performs comparably to high-performance baseline models on BLEU, METEOR, and ROUGE-L metrics, and outperformed the GPT-4o model on BLEU-2, BLEU-3, BLEU-4, and ROUGE-L metrics. The classification module significantly surpasses the state-of-the-art model in AUC and Accuracy. This demonstrates that the proposed model achieves high accuracy, readability, and fluency in report generation, while multimodal contrastive training with unlabelled radiograph-report pairs enhances classification performance.

Zhu Ting, Li Liangqi, Duan Shufei et al.

A multi-modal emotional speech Mandarin database including articulatory kinematics, acoustics, glottal and facial micro-expressions is designed and established, which is described in detail from the aspects of corpus design, subject selection, recording details and data processing. Where signals are labeled with discrete emotion labels (neutral, happy, pleasant, indifferent, angry, sad, grief) and dimensional emotion labels (pleasure, arousal, dominance). In this paper, the validity of dimension annotation is verified by statistical analysis of dimension annotation data. The SCL-90 scale data of annotators are verified and combined with PAD annotation data for analysis, so as to explore the internal relationship between the outlier phenomenon in annotation and the psychological state of annotators. In order to verify the speech quality and emotion discrimination of the database, this paper uses 3 basic models of SVM, CNN and DNN to calculate the recognition rate of these seven emotions. The results show that the average recognition rate of seven emotions is about 82% when using acoustic data alone. When using glottal data alone, the average recognition rate is about 72%. Using kinematics data alone, the average recognition rate also reaches 55.7%. Therefore, the database is of high quality and can be used as an important source for speech analysis research, especially for the task of multimodal emotional speech analysis.

Ting Zhu, Shufei Duan, Camille Dingam et al.

Dysarthria speech contains the pathological characteristics of vocal tract and vocal fold, but so far, they have not yet been included in traditional acoustic feature sets. Moreover, the nonlinearity and non-stationarity of speech have been ignored. In this paper, we propose a feature enhancement algorithm for dysarthria speech called WHFEMD. It combines empirical mode decomposition (EMD) and fast Walsh-Hadamard transform (FWHT) to enhance features. With the proposed algorithm, the fast Fourier transform of the dysarthria speech is first performed and then followed by EMD to get intrinsic mode functions (IMFs). After that, FWHT is used to output new coefficients and to extract statistical features based on IMFs, power spectral density, and enhanced gammatone frequency cepstral coefficients. To evaluate the proposed approach, we conducted experiments on two public pathological speech databases including UA Speech and TORGO. The results show that our algorithm performed better than traditional features in classification. We achieved improvements of 13.8% (UA Speech) and 3.84% (TORGO), respectively. Furthermore, the incorporation of an imbalanced classification algorithm to address data imbalance has resulted in a 12.18% increase in recognition accuracy. This algorithm effectively addresses the challenges of the imbalanced dataset and non-linearity in dysarthric speech and simultaneously provides a robust representation of the local pathological features of the vocal folds and tracts.

Zichuan Xu, Jiangkai Wu, Qiufen Xia et al.

With the development of deep learning technologies, attribute recognition and person re-identification (re-ID) have attracted extensive attention and achieved continuous improvement via executing computing-intensive deep neural networks in cloud datacenters. However, the datacenter deployment cannot meet the real-time requirement of attribute recognition and person re-ID, due to the prohibitive delay of backhaul networks and large data transmissions from cameras to datacenters. A feasible solution thus is to employ mobile edge clouds (MEC) within the proximity of cameras and enable distributed inference. In this paper, we design novel models for pedestrian attribute recognition with re-ID in an MEC-enabled camera monitoring system. We also investigate the problem of distributed inference in the MEC-enabled camera network. To this end, we first propose a novel inference framework with a set of distributed modules, by jointly considering the attribute recognition and person re-ID. We then devise a learning-based algorithm for the distributions of the modules of the proposed distributed inference framework, considering the dynamic MEC-enabled camera network with uncertainties. We finally evaluate the performance of the proposed algorithm by both simulations with real datasets and system implementation in a real testbed. Evaluation results show that the performance of the proposed algorithm with distributed inference framework is promising, by reaching the accuracies of attribute recognition and person identification up to 92.9% and 96.6% respectively, and significantly reducing the inference delay by at least 40.6% compared with existing methods.