Zhanpeng Jin

Chiyue Wang, Dong She, Yang Gao et al.

Electromyography (EMG) directly reflects muscle activation and is a key sensing modality for gesture recognition, prosthetic control, and wearable interaction. Existing EMG methods, however, commonly formulate hand action understanding as classification over fixed labels, making it difficult to support querying, retrieval, and generalization based on action descriptions. We present MyoSem, an EMG--action semantic alignment framework that maps low-level EMG signals into a shared semantic space constructed from multi-view action descriptions. MyoSem combines multi-view action-semantic construction, activation-aware EMG encoding, and semantic query alignment, enabling bidirectional retrieval between EMG signals and text descriptions. We systematically evaluate MyoSem on EMG2Pose and NinaPro-series datasets. Results show that MyoSem performs well on EMG--text bidirectional retrieval, generally outperforms most baselines, and shows favorable generalization to unseen users, held-out action classes, and amputee-user transfer scenarios. Ablations and visualizations further validate the effectiveness of each module. Overall, MyoSem advances EMG-based hand action understanding from fixed-label recognition toward queryable bidirectional semantic retrieval, providing a new modeling paradigm for language-mediated EMG action understanding.

Ping Yu, Wei Wang, Chunyuan Li et al.

Prompt tuning has been an extremely effective tool to adapt a pre-trained model to downstream tasks. However, standard prompt-based methods mainly consider the case of sufficient data of downstream tasks. It is still unclear whether the advantage can be transferred to the few-shot regime, where only limited data are available for each downstream task. Although some works have demonstrated the potential of prompt-tuning under the few-shot setting, the main stream methods via searching discrete prompts or tuning soft prompts with limited data are still very challenging. Through extensive empirical studies, we find that there is still a gap between prompt tuning and fully fine-tuning for few-shot learning. To bridge the gap, we propose a new prompt-tuning framework, called Soft Template Tuning (STT). STT combines manual and auto prompts, and treats downstream classification tasks as a masked language modeling task. Comprehensive evaluation on different settings suggests STT can close the gap between fine-tuning and prompt-based methods without introducing additional parameters. Significantly, it can even outperform the time- and resource-consuming fine-tuning method on sentiment classification tasks.

Hanhui Deng, Xinglin Li, Jie Luo et al.

Electrocardiogram is a useful diagnostic signal that can detect cardiac abnormalities by measuring the electrical activity generated by the heart. Due to its rapid, non-invasive, and richly informative characteristics, ECG has many emerging applications. In this paper, we study novel deep learning technologies to effectively manage and analyse ECG data, with the aim of building a diagnostic model, accurately and quickly, that can substantially reduce the burden on medical workers. Unlike the existing ECG models that exhibit a high misdiagnosis rate, our deep learning approaches can automatically extract the features of ECG data through end-to-end training. Specifically, we first devise EfficientECG, an accurate and lightweight classification model for ECG analysis based on the existing EfficientNet model, which can effectively handle high-frequency long-sequence ECG data with various leading types. On top of that, we next propose a cross-attention-based feature fusion model of EfficientECG for analysing multi-lead ECG data with multiple features (e.g., gender and age). Our evaluations on representative ECG datasets validate the superiority of our model against state-of-the-art works in terms of high precision, multi-feature fusion, and lightweights.

Yueru Sun, Yimeng Zhang, Haoyu Gu et al.

Multimodal Emotion Recognition (MER) is critical for interpreting real-world interactions. While Multimodal Large Language Models (MLLM) have shown promise in MER, their internal decision-making mechanisms under modality conflict and missingness remain largely underexplored. In this paper, to systematically investigate these behaviors, we introduce EmoMM, a comprehensive benchmark featuring modality-aligned, conflict, and missing subsets. Through extensive evaluation, we uncover a Video Contribution Collapse (VCC) phenomenon, where MLLM marginalize video evidence due to high token redundancy and modality preferences. To address this, we propose Conflict-aware Head-level Attention Steering (CHASE), a lightweight mechanism that detects modality conflicts and performs inference-time attention steering, effectively mitigating decision bias without retraining the backbone. Experimental results demonstrate that CHASE consistently improves performance across various settings, significantly enhancing the reliability of MLLM in complex affective scenarios.

Yuqin Yang, Haowu Zhou, Haoran Tu et al.

Most affective computing research treats emotion as a static property of text, focusing on the writer's sentiment while overlooking the reader's perspective. This approach ignores how individual personalities lead to diverse emotional appraisals of the same event. Although role-playing Large Language Models (LLMs) attempt to simulate such nuanced reactions, they often suffer from "personality illusion'' -- relying on surface-level stereotypes rather than authentic cognitive logic. A critical bottleneck is the absence of ground-truth human data to link personality traits to emotional shifts. To bridge the gap, we introduce Persona-E$^2$ (Persona-Event2Emotion), a large-scale dataset grounded in annotated MBTI and Big Five traits to capture reader-based emotional variations across news, social media, and life narratives. Extensive experiments reveal that state-of-the-art LLMs struggle to capture precise appraisal shifts, particularly in social media domains. Crucially, we find that personality information significantly improves comprehension, with the Big Five traits alleviating "personality illusion.'

Chengzhang Yu, Zening Lu, Chenyang Zheng et al.

Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel architecture featuring a million-scale external memory bank storing human-readable knowledge as token sequences, enabling direct inspection and modification. We design a differentiable two-stage retrieval mechanism with efficient coarse-grained filtering via product key decomposition (reducing complexity from $\mathcal{O}(N \cdot |I|)$ to $\mathcal{O}(\sqrt{N} \cdot |I|)$) and fine-grained Gumbel-Softmax matching for end-to-end training. Inspired by dual-system cognitive theory, we partition knowledge into frozen explicit facts (20%) and learnable implicit patterns (80%), maintained through Exponential Moving Average updates for stability. ExplicitLM achieves up to 43.67% improvement on knowledge-intensive tasks versus standard Transformers, with 3.62$\times$ gains in low-data regimes (10k samples). Analysis shows strong correlations between memory retrieval and performance, with correct predictions achieving 49% higher hit rates. Unlike RAG systems with frozen retrieval, our jointly optimized architecture demonstrates that interpretable, updatable models can maintain competitive performance while providing unprecedented knowledge transparency.

ChengZhang Yu, YingRu He, Hongyan Cheng et al.

Global healthcare systems face critical challenges from increasing patient volumes and limited consultation times, with primary care visits averaging under 5 minutes in many countries. While pre-consultation processes encompassing triage and structured history-taking offer potential solutions, they remain limited by passive interaction paradigms and context management challenges in existing AI systems. This study introduces a hierarchical multi-agent framework that transforms passive medical AI systems into proactive inquiry agents through autonomous task orchestration. We developed an eight-agent architecture with centralized control mechanisms that decomposes pre-consultation into four primary tasks: Triage ($T_1$), History of Present Illness collection ($T_2$), Past History collection ($T_3$), and Chief Complaint generation ($T_4$), with $T_1$--$T_3$ further divided into 13 domain-specific subtasks. Evaluated on 1,372 validated electronic health records from a Chinese medical platform across multiple foundation models (GPT-OSS 20B, Qwen3-8B, Phi4-14B), the framework achieved 87.0% accuracy for primary department triage and 80.5% for secondary department classification, with task completion rates reaching 98.2% using agent-driven scheduling versus 93.1% with sequential processing. Clinical quality scores from 18 physicians averaged 4.56 for Chief Complaints, 4.48 for History of Present Illness, and 4.69 for Past History on a 5-point scale, with consultations completed within 12.7 rounds for $T_2$ and 16.9 rounds for $T_3$. The model-agnostic architecture maintained high performance across different foundation models while preserving data privacy through local deployment, demonstrating the potential for autonomous AI systems to enhance pre-consultation efficiency and quality in clinical settings.

Dong She, Xianrong Yao, Liqun Chen et al.

Vision-Language Models (VLMs) have demonstrated strong capabilities in perception, yet holistic Affective Image Content Analysis (AICA), which integrates perception, reasoning, and generation into a unified framework, remains underexplored. To address this gap, we introduce AICA-Bench, a comprehensive benchmark with three core tasks: Emotion Understanding (EU), Emotion Reasoning (ER), and Emotion-Guided Content Generation (EGCG). We evaluate 23 VLMs and identify two major limitations: weak intensity calibration and shallow open-ended descriptions. To address these issues, we propose Grounded Affective Tree (GAT) Prompting, a training-free framework that combines visual scaffolding with hierarchical reasoning. Experiments show that GAT reduces intensity errors and improves descriptive depth, providing a strong baseline for future research on affective multimodal understanding and generation.

Chengzhang Yu, Yiming Zhang, Zhixin Liu et al.

The automation of scientific research through large language models (LLMs) presents significant opportunities but faces critical challenges in knowledge synthesis and quality assurance. We introduce Feedback-Refined Agent Methodology (FRAME), a novel framework that enhances medical paper generation through iterative refinement and structured feedback. Our approach comprises three key innovations: (1) A structured dataset construction method that decomposes 4,287 medical papers into essential research components through iterative refinement; (2) A tripartite architecture integrating Generator, Evaluator, and Reflector agents that progressively improve content quality through metric-driven feedback; and (3) A comprehensive evaluation framework that combines statistical metrics with human-grounded benchmarks. Experimental results demonstrate FRAME's effectiveness, achieving significant improvements over conventional approaches across multiple models (9.91% average gain with DeepSeek V3, comparable improvements with GPT-4o Mini) and evaluation dimensions. Human evaluation confirms that FRAME-generated papers achieve quality comparable to human-authored works, with particular strength in synthesizing future research directions. The results demonstrated our work could efficiently assist medical research by building a robust foundation for automated medical research paper generation while maintaining rigorous academic standards.

Xianrong Yao, Dong She, Chenxu Zhang et al.

Empathy is critical for effective mental health support, especially when addressing Long Counseling Texts (LCTs). However, existing Large Language Models (LLMs) often generate replies that are semantically fluent but lack the structured reasoning necessary for genuine psychological support, particularly in a Chinese context. To bridge this gap, we introduce Empathy-R1, a novel framework that integrates a Chain-of-Empathy (CoE) reasoning process with Reinforcement Learning (RL) to enhance response quality for LCTs. Inspired by cognitive-behavioral therapy, our CoE paradigm guides the model to sequentially reason about a help-seeker's emotions, causes, and intentions, making its thinking process both transparent and interpretable. Our framework is empowered by a new large-scale Chinese dataset, Empathy-QA, and a two-stage training process. First, Supervised Fine-Tuning instills the CoE's reasoning structure. Subsequently, RL, guided by a dedicated reward model, refines the therapeutic relevance and contextual appropriateness of the final responses. Experiments show that Empathy-R1 achieves strong performance on key automatic metrics. More importantly, human evaluations confirm its superiority, showing a clear preference over strong baselines and achieving a Win@1 rate of 44.30% on our new benchmark. By enabling interpretable and contextually nuanced responses, Empathy-R1 represents a significant advancement in developing responsible and genuinely beneficial AI for mental health support.

Hongyan Cheng, Chengzhang Yu, Yanshu Shi et al.

The post-pandemic surge in healthcare demand, coupled with critical nursing shortages, has placed unprecedented pressure on medical triage systems, necessitating innovative AI-driven solutions. We present a multi-agent interactive intelligent system for medical triage that addresses three fundamental challenges in current AI-based triage systems: inadequate medical specialization leading to misclassification, heterogeneous department structures across healthcare institutions, and inefficient detail-oriented questioning that impedes rapid triage decisions. Our system employs three specialized agents--RecipientAgent, InquirerAgent, and DepartmentAgent--that collaborate through Inquiry Guidance mechanism and Classification Guidance Mechanism to transform unstructured patient symptoms into accurate department recommendations. To ensure robust evaluation, we constructed a comprehensive Chinese medical triage dataset from "Ai Ai Yi Medical Network", comprising 3,360 real-world cases spanning 9 primary departments and 62 secondary departments. Experimental results demonstrate that our multi-agent system achieves 89.6% accuracy in primary department classification and 74.3% accuracy in secondary department classification after four rounds of patient interaction. The system's dynamic matching based guidance mechanisms enable efficient adaptation to diverse hospital configurations while maintaining high triage accuracy. We successfully developed this multi-agent triage system that not only adapts to organizational heterogeneity across healthcare institutions but also ensures clinically sound decision-making.

Shibo Zhou, Wei Wang, Xiaohua Li et al.

Event-driven sensors such as LiDAR and dynamic vision sensor (DVS) have found increased attention in high-resolution and high-speed applications. A lot of work has been conducted to enhance recognition accuracy. However, the essential topic of recognition delay or time efficiency is largely under-explored. In this paper, we present a spiking learning system that uses the spiking neural network (SNN) with a novel temporal coding for accurate and fast object recognition. The proposed temporal coding scheme maps each event's arrival time and data into SNN spike time so that asynchronously-arrived events are processed immediately without delay. The scheme is integrated nicely with the SNN's asynchronous processing capability to enhance time efficiency. A key advantage over existing systems is that the event accumulation time for each recognition task is determined automatically by the system rather than pre-set by the user. The system can finish recognition early without waiting for all the input events. Extensive experiments were conducted over a list of 7 LiDAR and DVS datasets. The results demonstrated that the proposed system had state-of-the-art recognition accuracy while achieving remarkable time efficiency. Recognition delay was shown to reduce by 56.3% to 91.7% in various experiment settings over the popular KITTI dataset.

Zijie Wang, Lixi Zhou, Amitabh Das et al.

Data is the king in the age of AI. However data integration is often a laborious task that is hard to automate. Schema change is one significant obstacle to the automation of the end-to-end data integration process. Although there exist mechanisms such as query discovery and schema modification language to handle the problem, these approaches can only work with the assumption that the schema is maintained by a database. However, we observe diversified schema changes in heterogeneous data and open data, most of which has no schema defined. In this work, we propose to use deep learning to automatically deal with schema changes through a super cell representation and automatic injection of perturbations to the training data to make the model robust to schema changes. Our experimental results demonstrate that our proposed approach is effective for two real-world data integration scenarios: coronavirus data integration, and machine log integration.

Di Wu, Huayan Wan, Siping Liu et al.

The "mind-controlling" capability has always been in mankind's fantasy. With the recent advancements of electroencephalograph (EEG) techniques, brain-computer interface (BCI) researchers have explored various solutions to allow individuals to perform various tasks using their minds. However, the commercial off-the-shelf devices to run accurate EGG signal collection are usually expensive and the comparably cheaper devices can only present coarse results, which prevents the practical application of these devices in domestic services. To tackle this challenge, we propose and develop an end-to-end solution that enables fine brain-robot interaction (BRI) through embedded learning of coarse EEG signals from the low-cost devices, namely DeepBrain, so that people having difficulty to move, such as the elderly, can mildly command and control a robot to perform some basic household tasks. Our contributions are two folds: 1) We present a stacked long short term memory (Stacked LSTM) structure with specific pre-processing techniques to handle the time-dependency of EEG signals and their classification. 2) We propose personalized design to capture multiple features and achieve accurate recognition of individual EEG signals by enhancing the signal interpretation of Stacked LSTM with attention mechanism. Our real-world experiments demonstrate that the proposed end-to-end solution with low cost can achieve satisfactory run-time speed, accuracy and energy-efficiency.

Wei Wang, Shibo Zhou, Jingxi Li et al.

Accurate real-time object recognition from sensory data has long been a crucial and challenging task for autonomous driving. Even though deep neural networks (DNNs) have been successfully applied in this area, most existing methods still heavily rely on the pre-processing of the pulse signals derived from LiDAR sensors, and therefore introduce additional computational overhead and considerable latency. In this paper, we propose an approach to address the object recognition problem directly with raw temporal pulses utilizing the spiking neural network (SNN). Being evaluated on various datasets (including Sim LiDAR, KITTI and DVS-barrel) derived from LiDAR and dynamic vision sensor (DVS), our proposed method has shown comparable performance as the state-of-the-art methods, while achieving remarkable time efficiency. It highlights the SNN's great potentials in autonomous driving and related applications. To the best of our knowledge, this is the first attempt to use SNN to directly perform object recognition on raw temporal pulses.

Amith K. Belman, Li Wang, S. S. Iyengar et al.

Behavioral biometrics are key components in the landscape of research in continuous and active user authentication. However, there is a lack of large datasets with multiple activities, such as typing, gait and swipe performed by the same person. Furthermore, large datasets with multiple activities performed on multiple devices by the same person are non-existent. The difficulties of procuring devices, participants, designing protocol, secure storage and on-field hindrances may have contributed to this scarcity. The availability of such a dataset is crucial to forward the research in behavioral biometrics as usage of multiple devices by a person is common nowadays. Through this paper, we share our dataset, the details of its collection, features for each modality and our findings of how keystroke features vary across devices. We have collected data from 117 subjects for typing (both fixed and free text), gait (walking, upstairs and downstairs) and touch on Desktop, Tablet and Phone. The dataset consists a total of about: 3.5 million keystroke events; 57.1 million data-points for accelerometer and gyroscope each; 1.7 million data-points for swipes; and enables future research to explore previously unexplored directions in inter-device and inter-modality biometrics. Our analysis on keystrokes reveals that in most cases, keyhold times are smaller but inter-key latencies are larger, on hand-held devices when compared to desktop. We also present; detailed comparison with related datasets; possible research directions with the dataset; and lessons learnt from the data collection.