arXiv subjects

Yuling Zhang

Publications and source records attributed to Yuling Zhang.

3 recordsLinked to original sources

arXiv2026

MedSWFlow: An Open-Source LLM Workflow for Drafting Medical Social Work Case Plans

We present MedSWFlow, an open-source, model-agnostic LLM workflow for drafting medical social work case plans. The framework translates professional case-planning tasks into six stages: assessment, problem analysis, goal setting, intervention planning, risk anticipation, and planned effect evaluation. Drawing on established social work and behavioral frameworks, MedSWFlow standardizes case inputs, builds structured case profiles, and generates reviewable assessment forms and service plans through staged prompting. The system is released as an open-source research framework for reproducible case-plan generation across LLM providers. Outputs are intended as practitioner-reviewed drafts rather than final service decisions. Source code: https://github.com/santhiyacw-droid/MedSWFlow/tree/main.

cs.HC↗

arXiv2025

Piezo1 Decodes Mechanical Forces via Allosteric Network Reprogramming

Understanding how molecular machines transduce mechanical force into chemical signals is a central goal in chemistry. The mechanosensitive ion channel Piezo1 is an archetypal nanoscale mechanotransducer, but the molecular principles by which it decodes distinct mechanical stimuli remain elusive. Here, we combine large-scale molecular dynamics simulations with time-series causal inference to elucidate the dynamic allosteric communication networks within Piezo1 under both quasi-static membrane tension and shockwave-induced cavitation. Under tangential tension, Piezo1 employs the lever-like pathway, a linear, feed-forward pathway propagating the signal from peripheral mechanophores to the central pore. In contrast, a shockwave impulse in the normal direction triggers a two-stage gating mechanism based on the dynamic reprogramming of the allosteric network. An initial compression phase activates an apical shortcut pathway originating from the cap domain. A subsequent tension phase utilizes a rewired network with complex feedback loops to drive the channel to a fully open state. These findings reveal that the allosteric wiring of a molecular machine is not static but can be dynamically reconfigured by the nature of the physical input. This principle of force-dependent pathway selection offers a new framework for understanding mechanochemistry and for designing programmable, stimuli-responsive molecular systems.

q-bio.MN↗

arXiv2024

Stable Heterogeneous Treatment Effect Estimation across Out-of-Distribution Populations

Heterogeneous treatment effect (HTE) estimation is vital for understanding the change of treatment effect across individuals or subgroups. Most existing HTE estimation methods focus on addressing selection bias induced by imbalanced distributions of confounders between treated and control units, but ignore distribution shifts across populations. Thereby, their applicability has been limited to the in-distribution (ID) population, which shares a similar distribution with the training dataset. In real-world applications, where population distributions are subject to continuous changes, there is an urgent need for stable HTE estimation across out-of-distribution (OOD) populations, which, however, remains an open problem. As pioneers in resolving this problem, we propose a novel Stable Balanced Representation Learning with Hierarchical-Attention Paradigm (SBRL-HAP) framework, which consists of 1) Balancing Regularizer for eliminating selection bias, 2) Independence Regularizer for addressing the distribution shift issue, 3) Hierarchical-Attention Paradigm for coordination between balance and independence. In this way, SBRL-HAP regresses counterfactual outcomes using ID data, while ensuring the resulting HTE estimation can be successfully generalized to out-of-distribution scenarios, thereby enhancing the model's applicability in real-world settings. Extensive experiments conducted on synthetic and real-world datasets demonstrate the effectiveness of our SBRL-HAP in achieving stable HTE estimation across OOD populations, with an average 10% reduction in the error metric PEHE and 11% decrease in the ATE bias, compared to the SOTA methods.

cs.LG↗