arXiv subjects

Zhoujian Sun

Publications and source records attributed to Zhoujian Sun.

15 recordsLinked to original sources

arXiv2026

Scattering-Induced Magnon Layer-Hall Transport beyond Band Geometry

The layer Hall effect has been exclusively attributed to layer-locked Berry curvature, posing a fundamental barrier to its realization in conventional magnets. Here we report a fundamentally distinct layer Hall effect for bosonic excitations, i.e., magnons, which originates solely from non-reciprocal dipolar scattering at heterointerfaces, thereby decoupling the phenomenon from geometric-phase mechanisms. Using a microscopic scattering theory, we demonstrate that a longitudinal temperature gradient drives opposite transverse thermal Hall currents in a nanowire atop a magnetic film, with the direction fully reconfigurable by the applied magnetic field. The effect yields a significant Hall angle of $\sim 6^{\circ}$ in conventional magnetic heterostructures, eliminating the need for topological engineering. Our findings establish a scattering-driven paradigm for layer Hall effect, extendable to ferrons and polar phonons, and predict a Hall response that is readily detectable in conventional magnetic heterostructures.

cond-mat.mes-hall↗

arXiv2026

Anisotropic Surface Spin Waves as Signature of A-type Altermagnets

Altermagnets have attracted intense interest because they have the advantages of both ferromagnets and antiferromagnets. However, their experimental identification remains challenging, in particular for the A-type altermagnets that account for a large group of material candidates. Here, we discover a kind of anisotropic surface spin waves in A-type altermagnets, which is absent in ferromagnets and conventional antiferromagnets. The anisotropic surface spin waves arise directly from the nature of altermagnets, i.e., the spin-opposite sublattices cannot be related by translation or inversion, which breaks the combined spatial-inversion and time-reversal symmetry, leading to the anisotropic surface spin waves with two properties, the chirality-dependent top-bottom positions and chiral split constant frequency contours. We further show that these two properties can be measured experimentally from the stray field and by resonance absorption spectrum, respectively. Our results provide a signature for detecting altermagnets and will inspire spin-based logic and information-storage devices.

cond-mat.mes-hall↗

arXiv2025

anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understanding

The advent of multimodal large language models (MLLMs) has sparked interest in their application to electrocardiogram (ECG) analysis. However, existing ECG-focused MLLMs primarily focus on report generation tasks, often limited to single 12-lead, short-duration (10s) ECG inputs, thereby underutilizing the potential of MLLMs. To this end, we aim to develop a MLLM for ECG analysis that supports a broader range of tasks and more flexible ECG inputs. However, existing ECG-QA datasets are often monotonous. To address this gap, we first constructed the anyECG dataset, which encompasses a wide variety of tasks, including report generation, abnormal waveform localization, and open-ended question answering. In addition to standard hospital ECGs, we introduced long-duration reduced-lead ECGs for home environments and multiple ECG comparison scenarios commonly encountered in clinical practice. Furthermore, we propose the anyECG-chat model, which supports dynamic-length ECG inputs and multiple ECG inputs. We trained the model using a three-stage curriculum training recipe with the anyECG dataset. A comprehensive evaluation was conducted, demonstrating that anyECG-chat is capable of supporting various practical application scenarios, including not only common report generation tasks but also abnormal waveform localization for long-duration reduced-lead ECGs in home environments and comprehensive comparative analysis of multiple ECGs. Our code and data are available at: https://github.com/CuCl-2/anyECG-chat.

cs.CL↗

arXiv2025

Lessons Learned from Evaluation of LLM based Multi-agents in Safer Therapy Recommendation

Therapy recommendation for chronic patients with multimorbidity is challenging due to risks of treatment conflicts. Existing decision support systems face scalability limitations. Inspired by the way in which general practitioners (GP) manage multimorbidity patients, occasionally convening multidisciplinary team (MDT) collaboration, this study investigated the feasibility and value of using a Large Language Model (LLM)-based multi-agent system (MAS) for safer therapy recommendations. We designed a single agent and a MAS framework simulating MDT decision-making by enabling discussion among LLM agents to resolve medical conflicts. The systems were evaluated on therapy planning tasks for multimorbidity patients using benchmark cases. We compared MAS performance with single-agent approaches and real-world benchmarks. An important contribution of our study is the definition of evaluation metrics that go beyond the technical precision and recall and allow the inspection of clinical goals met and medication burden of the proposed advices to a gold standard benchmark. Our results show that with current LLMs, a single agent GP performs as well as MDTs. The best-scoring models provide correct recommendations that address all clinical goals, yet the advices are incomplete. Some models also present unnecessary medications, resulting in unnecessary conflicts between medication and conditions or drug-drug interactions.

cs.AI↗

arXiv2025

Exchange Surface Spin Waves in Type-A van der Waals Antiferromagnets

Surface spin waves in the short-wavelength regime enable ultrafast, nanoscale magnon-based devices. Here we report the emergence of surface spin-wave excitations within the bulk magnon band gap of type-A van der Waals antiferromagnets composed of antiferromagnetically coupled ferromagnetic monolayers. In contrast to the magnetostatic Damon-Eshbach modes in magnetic slabs, these surface waves are pure exchange modes owing to the reduced interlayer exchange coupling at surface layers, and thus persist in ultrathin multilayer stacks and at large wave numbers. We show that they can be efficiently excited by electromagnetic waves, with absorption power comparable to or even exceeding that of bulk modes. Moreover, their magnetic stray fields exhibit pronounced even-odd oscillations with the number of monolayers that should be observable by NV-center magnetometry.

cond-mat.mes-hall↗

arXiv2025

Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning

Recent advances in large language models (LLMs) have shown promising results in medical diagnosis, with some studies indicating superior performance compared to human physicians in specific scenarios. However, the diagnostic capabilities of LLMs are often overestimated, as their performance significantly deteriorates in interactive diagnostic settings that require active information gathering. This study investigates the underlying mechanisms behind the performance degradation phenomenon and proposes a solution. We identified that the primary deficiency of LLMs lies in the initial diagnosis phase, particularly in information-gathering efficiency and initial diagnosis formation, rather than in the subsequent differential diagnosis phase. To address this limitation, we developed a plug-and-play method enhanced (PPME) LLM agent, leveraging over 3.5 million electronic medical records from Chinese and American healthcare facilities. Our approach integrates specialized models for initial disease diagnosis and inquiry into the history of the present illness, trained through supervised and reinforcement learning techniques. The experimental results indicate that the PPME LLM achieved over 30% improvement compared to baselines. The final diagnostic accuracy of the PPME LLM in interactive diagnostic scenarios approached levels comparable to those achieved using complete clinical data. These findings suggest a promising potential for developing autonomous diagnostic systems, although further validation studies are needed.

cs.AI↗

arXiv2024

De-biased Multimodal Electrocardiogram Analysis

Multimodal large language models (MLLMs) are increasingly being applied in the medical field, particularly in medical imaging. However, developing MLLMs for ECG signals, which are crucial in clinical settings, has been a significant challenge beyond medical imaging. Previous studies have attempted to address this by converting ECGs into several text tags using an external classifier in a training-free manner. However, this approach significantly compresses the information in ECGs and underutilizes the reasoning capabilities of LLMs. In this work, we directly feed the embeddings of ECGs into the LLM through a projection layer, retaining more information about ECGs and better leveraging the reasoning abilities of LLMs. Our method can also effectively handle a common situation in clinical practice where it is necessary to compare two ECGs taken at different times. Recent studies found that MLLMs may rely solely on text input to provide answers, ignoring inputs from other modalities. We analyzed this phenomenon from a causal perspective in the context of ECG MLLMs and discovered that the confounder, severity of illness, introduces a spurious correlation between the question and answer, leading the model to rely on this spurious correlation and ignore the ECG input. Such models do not comprehend the ECG input and perform poorly in adversarial tests where different expressions of the same question are used in the training and testing sets. We designed a de-biased pre-training method to eliminate the confounder's effect according to the theory of backdoor adjustment. Our model performed well on the ECG-QA task under adversarial testing and demonstrated zero-shot capabilities. An interesting random ECG test further validated that our model effectively understands and utilizes the input ECG signal.

cs.CL↗

arXiv2024

Kibble-Zurek Behavior in the Boundary-obstructed Phase Transitions

We study the nonadiabatic dynamics of a two-dimensional higher-order topological insulator when the system is slowly quenched across the boundary-obstructed phase transition, which is characterized by edge band gap closing. We find that the number of excitations produced after the quench exhibits power-law scaling behaviors with the quench rate. Boundary conditions can drastically modify the scaling behaviors: The scaling exponent is found to be $α=1/2$ for hybridized and fully open boundary conditions, and $α=2$ for periodic boundary condition. We argue that the exponent $α=1/2$ cannot be explained by the Kibble-Zurek mechanism unless we adopt an effective dimension $d^{\rm eff}=1$ instead of the real dimension $d=2$. For comparison, we also investigate the slow quench dynamics across the bulk-obstructed phase transitions and a single multicritical point, which obeys the Kibble-Zurek mechanism with dimension $d=2$.

cond-mat.stat-mech↗

arXiv2024

Conversational Disease Diagnosis via External Planner-Controlled Large Language Models

The development of large language models (LLMs) has brought unprecedented possibilities for artificial intelligence (AI) based medical diagnosis. However, the application perspective of LLMs in real diagnostic scenarios is still unclear because they are not adept at collecting patient data proactively. This study presents a LLM-based diagnostic system that enhances planning capabilities by emulating doctors. Our system involves two external planners to handle planning tasks. The first planner employs a reinforcement learning approach to formulate disease screening questions and conduct initial diagnoses. The second planner uses LLMs to parse medical guidelines and conduct differential diagnoses. By utilizing real patient electronic medical record data, we constructed simulated dialogues between virtual patients and doctors and evaluated the diagnostic abilities of our system. We demonstrated that our system obtained impressive performance in both disease screening and differential diagnoses tasks. This research represents a step towards more seamlessly integrating AI into clinical settings, potentially enhancing the accuracy and accessibility of medical diagnostics.

cs.CL↗

arXiv2024

Universal scalefree non-Hermitian skin effect near the Bloch point

The scalefree non-Hermitian skin effect (NHSE) refers to the phenomenon that the localization length of skin modes scales proportionally with system size in non-Hermitian systems. Authors of recent studies have demonstrated that the scalefree NHSE can be induced through various mechanisms, including the critical NHSE, local non-Hermiticity, and the boundary impurity effect. Nevertheless, these methods require careful modeling and precise parameter tuning. In contrast, in this paper, we suggest that the scalefree NHSE is a universal phenomenon, observable in extensive systems if these systems can be described by non-Bloch band theory and host Bloch points on the energy spectrum in the thermodynamic limit. Crucially, we discover that the geometry of the generalized Brillouin zone determines the scaling rule of the localization length, which can scale either linearly or quadratically with the system size. In this paper, we enriches the phenomenon of the scalefree NHSE.

quant-ph↗

arXiv2023

CTP:A Causal Interpretable Model for Non-Communicable Disease Progression Prediction

Non-communicable disease is the leading cause of death, emphasizing the need for accurate prediction of disease progression and informed clinical decision-making. Machine learning (ML) models have shown promise in this domain by capturing non-linear patterns within patient features. However, existing ML-based models cannot provide causal interpretable predictions and estimate treatment effects, limiting their decision-making perspective. In this study, we propose a novel model called causal trajectory prediction (CTP) to tackle the limitation. The CTP model combines trajectory prediction and causal discovery to enable accurate prediction of disease progression trajectories and uncover causal relationships between features. By incorporating a causal graph into the prediction process, CTP ensures that ancestor features are not influenced by the treatment of descendant features, thereby enhancing the interpretability of the model. By estimating the bounds of treatment effects, even in the presence of unmeasured confounders, the CTP provides valuable insights for clinical decision-making. We evaluate the performance of the CTP using simulated and real medical datasets. Experimental results demonstrate that our model achieves satisfactory performance, highlighting its potential to assist clinical decisions. Source code is in \href{https://github.com/DanielSun94/CFPA}{here}.

cs.LG↗

arXiv2023

Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement learning (RL) frameworks cannot imitate humans well. Training RL models require online interactions with user simulators, while simulating complex human policy is hard. Performances of SL-based models are restricted because of the covariate shift problem. Specifically, a dialogue is a sequential decision-making process where slight differences in current utterances and actions will cause significant differences in subsequent utterances. Therefore, the generalize ability of SL models is restricted because statistical characteristics of training and testing dialogue data gradually become different. This study proposed an offline imitation learning model that learns policy from real dialogue datasets and does not require user simulators. It also utilizes state transition information, which alleviates the influence of the covariate shift problem. We introduced a regularization trick to make our model can be effectively optimized. We investigated the performance of our model on four independent public dialogue datasets. The experimental result showed that our model performed better in the action prediction task.

cs.CL↗

arXiv2023

Interpretable Disease Prediction based on Reinforcement Path Reasoning over Knowledge Graphs

Objective: To combine medical knowledge and medical data to interpretably predict the risk of disease. Methods: We formulated the disease prediction task as a random walk along a knowledge graph (KG). Specifically, we build a KG to record relationships between diseases and risk factors according to validated medical knowledge. Then, a mathematical object walks along the KG. It starts walking at a patient entity, which connects the KG based on the patient current diseases or risk factors and stops at a disease entity, which represents the predicted disease. The trajectory generated by the object represents an interpretable disease progression path of the given patient. The dynamics of the object are controlled by a policy-based reinforcement learning (RL) module, which is trained by electronic health records (EHRs). Experiments: We utilized two real-world EHR datasets to evaluate the performance of our model. In the disease prediction task, our model achieves 0.743 and 0.639 in terms of macro area under the curve (AUC) in predicting 53 circulation system diseases in the two datasets, respectively. This performance is comparable to the commonly used machine learning (ML) models in medical research. In qualitative analysis, our clinical collaborator reviewed the disease progression paths generated by our model and advocated their interpretability and reliability. Conclusion: Experimental results validate the proposed model in interpretably evaluating and optimizing disease prediction. Significance: Our work contributes to leveraging the potential of medical knowledge and medical data jointly for interpretable prediction tasks.

cs.LG↗

arXiv2022

Field-driven side-by-side magnetic domain wall dynamics in ferromagnetic nanostrips

There has been a plethora of studies on domain wall dynamics in magnetic nanostrips, mainly because of its versatile non-linear physics and potential applications in data storage devices. However, most of the studies focus on out-of-plane domain walls or in-plane head-to-head (tail-to-tail) domain walls. Here, we numerically study the field-driven dynamics of in-plane side-by-side domain walls in ferromagnetic strips, which can be stable in the presence of an in-plane easy-axis anisotropy transverse to the strip. The domain walls move in a rigid-body manner at low field, and show complex Walker breakdown behavior at high field. We observe a multi-step Walker breakdown through vortex nucleation in wide strips. In the presence of Dzyaloshinskii-Moriya interaction (DMI), the first Walker breakdown field first decreases then increases with interfacial DMI, while keeps increasing with bulk DMI. These findings complement the current understanding on domain wall dynamics.

cond-mat.mes-hall↗

arXiv2022

On Tracking Dialogue State by Inheriting Slot Values in Mentioned Slot Pools

Dialogue state tracking (DST) is a component of the task-oriented dialogue system. It is responsible for extracting and managing slot values according to dialogue utterances, where each slot represents an essential part of the information to accomplish a task, and slot value is updated recurrently in each dialogue turn. However, many DST models cannot update slot values appropriately. These models may repeatedly inherit wrong slot values extracted in previous turns, resulting in the fail of the entire DST task. They cannot update indirectly mentioned slots well, either. This study designed a model with a mentioned slot pool (MSP) to tackle the update problem. The MSP is a slot-specific memory that records all mentioned slot values that may be inherited, and our model updates slot values according to the MSP and the dialogue context. Our model rejects inheriting the previous slot value when it predicates the value is wrong. Then, it re-extracts the slot value from the current dialogue context. As the contextual information accumulates with the dialogue progress, the new value is more likely to be correct. It also can track the indirectly mentioned slot by picking a value from the MSP. Experimental results showed our model reached state-of-the-art DST performance on MultiWOZ 2.1 and 2.2 datasets.

cs.CL↗