arXiv subjects

Weilin Wang

Publications and source records attributed to Weilin Wang.

5 recordsLinked to original sources

arXiv2026

Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance

Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly outputs risk score-based staging, ranked guideline-consistent treatments with evidence-based rationales, and individualized survival estimates. We curated about 30,000 HCC cases from SEER and expanded them into EMR-style narrative training data using a clinician-validated, prompt-based augmentation workflow. On this corpus, we developed a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward, moving beyond text-level memorization of clinical guidelines. In a multi-center cohort of 6,668 patients from 12 hospitals in China, HCC-STAR achieved state-of-the-art performance in treatment recommendation and risk stratification compared with clinical guidelines and competitive models, including GPT-5 and Gemini-2.5 Pro. Hypothetical overall-survival analysis showed a median survival of 51 months under adherence to HCC-STAR recommendations, compared with 29 and 32 months under BCLC and CNLC. In clinician-centric evaluations, blinded hepatobiliary specialists rated HCC-STAR's reasoning and evidence-based justifications as trustworthy. The model surpassed resident and attending physicians in treatment accuracy and helped physicians make more accurate decisions faster when used as an assistant. These findings support HCC-STAR as a reliable and verifiable decision-support system for risk stratification and precision therapy in HCC.

cs.AI↗

arXiv2026

Superradiant Phase Transition and Statistical Properties in the Dicke-Stark Model

In this study, the energy spectrum and thermal equilibrium states of the finite-size Dicke-Stark model were numerically obtained within the extended coherent state space by solving the dressed master equation for strongly coupled light-atom systems. The critical point of the superradiant phase transition in the infinite-size Dicke-Stark model was analytically derived using the mean-field approach and confirmed with numerical calculation. Under thermal equilibrium conditions, analyses of the negativity, zero-time-delay two-photon correlation function, and atom-spin squeezing parameters in the finite-size Dicke-Stark model reveal that as the coupling strength increases, the light field undergoes a transition from photon bunching to anti-bunching and then back to bunching. The Stark field can modulate both the maximum and minimum values of the two-photon correlation function and their corresponding coupling strengths. At low temperatures, the system exhibits entanglement and spin squeezing. As temperature rises, entanglement gradually diminishes, while strong coupling facilitates the preservation of entanglement in the system state. Atom-spin squeezing spin squeezing is highly sensitive to temperature and vanishes rapidly with increasing temperature. This work contributes to the fundamental understanding of quantum phenomena in Dicke-Stark systems.

quant-ph↗

arXiv2025

What Can Student-AI Dialogues Tell Us About Students' Self-Regulated Learning? An exploratory framework

The rise of Human-AI Collaborative Learning (HAICL) is shifting education toward dialogue-centric paradigms, creating an urgent need for new assessment methods. Evaluating Self-Regulated Learning (SRL) in this context presents new challenges, as the limitations of conventional approaches become more apparent. Questionnaires remain interrupted, while the utility of non-interrupted metrics like clickstream data is diminishing as more learning activity occurs within the dialogue. This study therefore investigates whether the student-AI dialogue can serve as a valid, non-interrupted data source for SRL assessment. We analyzed 421 dialogue logs from 98 university students interacting with a generative AI (GenAI) learning partner. Using large language model embeddings and clustering, we identified 22 dialogue patterns and quantified each student's interaction as a profile of alignment scores, which were analyzed against their Online Self-Regulated Learning Questionnaire (OSLQ) scores. Findings revealed a significant positive association between proactive dialogue patterns (e.g., post-class knowledge integration) and overall SRL. Conversely, reactive patterns (e.g., foundational pre-class questions) were significantly and negatively associated with overall SRL and its sub-processes. A group comparison substantiated these results, with low-SRL students showing significantly higher alignment with reactive patterns than their high-SRL counterparts. This study proposed the Dialogue-Based Human-AI Self-Regulated Learning (DHASRL) framework, a practical methodology for embedding SRL assessment directly within the HAICL dialogue to enable real-time monitoring and scaffolding of student regulation.

cs.CY↗

arXiv2025

Quantum Otto Heat Engine based on the Dicke-Stark Model under Infinite-Time and Finite-Time Thermodynamic Frameworks

We propose a quantum Otto heat engine that employs a finite-size Dicke-Stark model as the working substance. In the extended coherent state space, the complete energy spectrum and eigenstates of this model are obtained through numerical calculations. Within the infinite-time and finite-time thermodynamics frameworks, we investigate the effects of the Stark field strength, coupling strength, adiabatic stroke time, isochoric stroke time, and number of atoms in the DS model on the heat engine's output work, efficiency, and power. The results show that the maximum values of the output work and efficiency appear near the coupling strength corresponding to the superradiant phase transition point. Regulating the Stark field strength can tune the energy level structure of the system and the superradiant phase transition, effectively reducing entropy generation and quantum friction during nonequilibrium evolution of the system's states and thereby significantly increasing the engine's output work, efficiency, and power. Asymmetric heat engines, where the two isochoric strokes have different Stark field strengths and stroke times, are more conducive to optimizing the heat engine's performance. Additionally, in the DS model, an increase in the number of atoms is also beneficial for increasing the heat engine's output work and efficiency. The results of this paper facilitate the design of high-performance quantum heat engines.

quant-ph↗

arXiv2019

3D characterization of the primary Al3Sc phases in an Al-Sc alloy using Synchrotron X-ray tomography and electron microscopy

The three-dimensional structures of the primary Al3Sc particles in an Al-2Sc master alloy were studied by synchrotron X-ray microtomography, scanning and transmission electron microscopy. The Al3Sc phases were found to be a single cube and a cluster of cubes. The surface area, equivalent diameter of the Al3Sc cubes increased with the increasing of cube volume, but the specific surface area decreases. The primary Al3Sc cubes and Al-matrix have the same crystal orientation, indicating that the Al3Sc phases are the heterogeneous nucleation sites for Al. The experimental results show that α-Al2O3 are the possible nucleation sites for the Al3Sc cubes.

cond-mat.mtrl-sci↗