Searcharxiv⌕ Search

arXiv subjects

Kui Chen

Publications and source records attributed to Kui Chen.

15 recordsLinked to original sources
arXiv2026

From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM

Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models.

cs.CL↗
arXiv2026

DERM-3R: A Resource-Efficient Multimodal Agents Framework for Dermatologic Diagnosis and Treatment in Real-World Clinical Settings

Dermatologic diseases impose a large and growing global burden, affecting billions and substantially reducing quality of life. While modern therapies can rapidly control acute symptoms, long-term outcomes are often limited by single-target paradigms, recurrent courses, and insufficient attention to systemic comorbidities. Traditional Chinese medicine (TCM) provides a complementary holistic approach via syndrome differentiation and individualized treatment, but practice is hindered by non-standardized knowledge, incomplete multimodal records, and poor scalability of expert reasoning. We propose DERM-3R, a resource-efficient multimodal agent framework to model TCM dermatologic diagnosis and treatment under limited data and compute. Based on real-world workflows, we reformulate decision-making into three core issues: fine-grained lesion recognition, multi-view lesion representation with specialist-level pathogenesis modeling, and holistic reasoning for syndrome differentiation and treatment planning. DERM-3R comprises three collaborative agents: DERM-Rec, DERM-Rep, and DERM-Reason, each targeting one component of this pipeline. Built on a lightweight multimodal LLM and partially fine-tuned on 103 real-world TCM psoriasis cases, DERM-3R performs strongly across dermatologic reasoning tasks. Evaluations using automatic metrics, LLM-as-a-judge, and physician assessment show that despite minimal data and parameter updates, DERM-3R matches or surpasses large general-purpose multimodal models. These results suggest structured, domain-aware multi-agent modeling can be a practical alternative to brute-force scaling for complex clinical tasks in dermatology and integrative medicine.

cs.AI↗
arXiv2026

MedExChain: Enabling Secure and Efffcient PHR Sharing Across Heterogeneous Blockchains

With the proliferation of intelligent healthcare systems, patients' Personal Health Records (PHR) generated by the Internet of Medical Things (IoMT) in real-time play a vital role in disease diagnosis. The integration of emerging blockchain technologies signiffcantly enhanced the data security inside intelligent medical systems. However, data sharing across different systems based on varied blockchain architectures is still constrained by the unsolved performance and security challenges. This paper constructs a cross-chain data sharing scheme, termed MedExChain, which aims to securely share PHR across heterogeneous blockchain systems. The MedExChain scheme ensures that PHR can be shared across chains even under the performance limitations of IoMT devices. Additionally, the scheme incorporates Cryptographic Reverse Firewall (CRF) and a blockchain audit mechanism to defend against both internal and external security threats. The robustness of our scheme is validated through BAN logic, Scyther tool, Chosen Plaintext Attack (CPA) and Algorithm Substitution Attack (ASA) security analysis veriffcation. Extensive evaluations demonstrate that MedExChain signiffcantly minimizes computation and communication overhead, making it suitable for IoMT devices and fostering the efffcient circulation of PHR across diverse blockchain systems.

cs.CR↗
arXiv2025

AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization

Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension, resulting in a larger key-value (KV) cache compared to static image embedding. A naive optimization strategy is to selectively focus on and retain KV caches of audio or video based on task. However, in the experiment, we observed that the attention of AV-LLMs to various modalities in the high layers is not strictly dependent on the task. In higher layers, the attention of AV-LLMs shifts more towards the video modality. In addition, we also found that directly integrating temporal KV of audio and spatial-temporal KV of video may lead to information confusion and significant performance degradation of AV-LLMs. If audio and video are processed indiscriminately, it may also lead to excessive compression or reservation of a certain modality, thereby disrupting the alignment between modalities. To address these challenges, we propose AccKV, an Adaptive-Focusing and Cross-Calibration KV cache optimization framework designed specifically for efficient AV-LLMs inference. Our method is based on layer adaptive focusing technology, selectively focusing on key modalities according to the characteristics of different layers, and enhances the recognition of heavy hitter tokens through attention redistribution. In addition, we propose a Cross-Calibration technique that first integrates inefficient KV caches within the audio and video modalities, and then aligns low-priority modalities with high-priority modalities to selectively evict KV cache of low-priority modalities. The experimental results show that AccKV can significantly improve the computational efficiency of AV-LLMs while maintaining accuracy.

cs.MM↗
arXiv2025

Tianyi: A Traditional Chinese Medicine all-rounder language model and its Real-World Clinical Practice

Natural medicines, particularly Traditional Chinese Medicine (TCM), are gaining global recognition for their therapeutic potential in addressing human symptoms and diseases. TCM, with its systematic theories and extensive practical experience, provides abundant resources for healthcare. However, the effective application of TCM requires precise syndrome diagnosis, determination of treatment principles, and prescription formulation, which demand decades of clinical expertise. Despite advancements in TCM-based decision systems, machine learning, and deep learning research, limitations in data and single-objective constraints hinder their practical application. In recent years, large language models (LLMs) have demonstrated potential in complex tasks, but lack specialization in TCM and face significant challenges, such as too big model scale to deploy and issues with hallucination. To address these challenges, we introduce Tianyi with 7.6-billion-parameter LLM, a model scale proper and specifically designed for TCM, pre-trained and fine-tuned on diverse TCM corpora, including classical texts, expert treatises, clinical records, and knowledge graphs. Tianyi is designed to assimilate interconnected and systematic TCM knowledge through a progressive learning manner. Additionally, we establish TCMEval, a comprehensive evaluation benchmark, to assess LLMs in TCM examinations, clinical tasks, domain-specific question-answering, and real-world trials. The extensive evaluations demonstrate the significant potential of Tianyi as an AI assistant in TCM clinical practice and research, bridging the gap between TCM knowledge and practical application.

cs.CL↗
arXiv2024

Cross-chain Sharing of Personal Health Records: Heterogeneous and Interoperable Blockchains

With the widespread adoption of medical informatics, a wealth of valuable personal health records (PHR) has been generated. Concurrently, blockchain technology has enhanced the security of medical institutions. However, these institutions often function as isolated data silos, limiting the potential value of PHRs. As the demand for data sharing between hospitals on different blockchains grows, addressing the challenge of cross-chain data sharing becomes crucial. When sharing PHRs across blockchains, the limited storage and computational capabilities of medical Internet of Things (IoT) devices complicate the storage of large volumes of PHRs and the handling of complex calculations. Additionally, varying blockchain cryptosystems and the risk of internal attacks further complicate the cross-chain sharing of PHRs. This paper proposes a scheme for sharing PHRs across heterogeneous and interoperable blockchains. Medical IoT devices can encrypt and store real-time PHRs in an InterPlanetary File System, requiring only simple operations for data sharing. An enhanced proxy re-encryption(PRE) algorithm addresses the differences in blockchain cryptosystems. Multi-dimensional analysis demonstrates that this scheme offers robust security and excellent performance.

cs.CR↗
arXiv2024

NPAT Null-Space Projected Adversarial Training Towards Zero Deterioration

To mitigate the susceptibility of neural networks to adversarial attacks, adversarial training has emerged as a prevalent and effective defense strategy. Intrinsically, this countermeasure incurs a trade-off, as it sacrifices the model's accuracy in processing normal samples. To reconcile the trade-off, we pioneer the incorporation of null-space projection into adversarial training and propose two innovative Null-space Projection based Adversarial Training(NPAT) algorithms tackling sample generation and gradient optimization, named Null-space Projected Data Augmentation (NPDA) and Null-space Projected Gradient Descent (NPGD), to search for an overarching optimal solutions, which enhance robustness with almost zero deterioration in generalization performance. Adversarial samples and perturbations are constrained within the null-space of the decision boundary utilizing a closed-form null-space projector, effectively mitigating threat of attack stemming from unreliable features. Subsequently, we conducted experiments on the CIFAR10 and SVHN datasets and reveal that our methodology can seamlessly combine with adversarial training methods and obtain comparable robustness while keeping generalization close to a high-accuracy model.

cs.LG↗
arXiv2024

The integrable semi-discrete nonlinear Schr\"odinger equations with nonzero backgrounds: Bilinearization-reduction approach

In this paper the classical and nonlocal semi-discrete nonlinear Schr\"{o}dinger (sdNLS) equations with nonzero backgrounds are solved by means of the bilinearization-reduction approach. In the first step of this approach, the unreduced sdNLS system with a nonzero background is bilinearized and its solutions are presented in terms of quasi double Casoratians. Then, reduction techniques are implemented to deal with complex and nonlocal reductions, which yields solutions for the four classical and nonlocal sdNLS equations with a plane wave background or a hyperbolic function background. These solutions are expressed with explicit formulae and allow classifications according to canonical forms of certain spectral matrix. In particular, we present explicit formulae for general rogue waves for the classical focusing sdNLS equation. Some obtained solutions are analyzed and illustrated.

nlin.SI↗
arXiv2020

Modular WSS-based OXCs for Large-Scale Optical Networks

The explosive growth of broadband applications calls for large-scale optical cross-connects (OXCs). However, the classical wavelength selective switch (WSS) based OXC is not scalable in terms of the size of employed WSSs and the cabling complexity. To solve this problem, we propose a three-phase approach to construct a modular WSS-based OXC. In phase 1, we factorize the interconnection network between the input stage and the output stage of the traditional OXC into a set of small-size interconnection networks. In phase 2, we decompose each WSS into a two-stage cascaded structure of small-size WSSs. In phase 3, we combine the small-size interconnection networks with the small-size WSSs to form a set of small-size OXC modules. At last, we obtain a modular OXC, which is a network of small-size OXCs. Similar to the classical OXC, the modular OXC is nonblocking at each wavelength and possesses a self-routing property. Our analysis shows that the modular OXC has small cabling complexity and acceptable physical-layer performance.

cs.NI↗
arXiv2019

Squared eigenfunction symmetry of the D$\Delta$mKP hierarchy and its constraint

In this paper squared eigenfunction symmetry of the differential-difference modified Kadomtsev-Petviashvili (D$\Delta$mKP) hierarchy and its constraint are considered. Under the constraint, the Lax triplets of the D$\Delta$mKP hierarchy, together with their adjoint forms, give rise to the positive relativistic Toda (R-Toda) hierarchy. An invertible transformation is given to connect the positive and negative R-Toda hierarchies. The positive R-Toda hierarchy is reduced to the differential-difference Burgers hierarchy. We also consider another D$\Delta$mKP hierarchy and show that its squared eigenfunction symmetry constraint gives rise to the Volterra hierarchy. In addition, we revisit the Ragnisco-Tu hierarchy which is a squared eigenfunction symmetry constraint of the differential-difference Kadomtsev-Petviashvili (D$\Delta$KP) system. It was thought the Ragnisco-Tu hierarchy does not exist one-field reduction, but here we find an one-field reduction to reduce the hierarchy to the Volterra hierarchy. Besides, the differential-difference Burgers hierarchy are also investigated in Appendix. A multi-dimensionally consistent 3-point discrete Burgers equation is given.

nlin.SI↗
arXiv2017

Solutions of local and nonlocal equations reduced from the AKNS hierarchy

In the paper possible local and nonlocal reductions of the Ablowitz-Kaup-Newell-Suger (AKNS) hierarchy are collected, including the Korteweg-de Vries (KdV) hierarchy, modified KdV hierarchy and their nonlocal versions, nonlinear Schr\"{o}dinger hierarchy and their nonlocal versions, sine-Gordon equation in nonpotential form and its nonlocal forms. A reduction technique for solutions is employed, by which exact solutions in double Wronskian form are obtained for these reduced equations from those double Wronskian solutions of the AKNS hierarchy. As examples of dynamics we illustrate new interaction of two-soliton solutions of the reverse-$t$ nonlinear Schr\"{o}dinger equation. Although as a single soliton it is always stationary, two solitons travel along completely symmetric trajectories in $\{x,t\}$ plane and their amplitudes are affected by phase parameters. Asymptotic analysis is given as demonstration. The approach and relation described in this paper are systematic and general and can be used to other nonlocal equations.

nlin.SI↗
arXiv2017

Solutions of the nonlocal nonlinear Schr\"odinger hierarchy via reduction

In this letter we propose an approach to obtain solutions for the nonlocal nonlinear Schr\"{o}dinger hierarchy from the known ones of the Ablowitz-Kaup-Newell-Segur hierarchy by reduction. These solutions are presented in terms of double Wronskian and some of them are new.The approach is general and can be used for other systems with double Wronskian solutions which admit local and nonlocal reductions.

nlin.SI↗
arXiv2016

On a Second Discretization of the ZS-AKNS Spectral Problem: Revisit

In this paper we revisit a discrete spectral problem which was proposed by Ragnisco and Tu in 1989, as a second discretization of the ZS-AKNS spectral problem. We show that the spectral problem corresponds to a bidirectional discretization of the derivative of two wave functions $\phi_{1,x}$ and $\phi_{2,x}$. As a connection with higher dimensional systems, the spectral problem and a related hierarchy can be derived from Lax triads of the differential-difference KP hierarchy via a symmetry constraint. Isospectral and nonisospectral flows derived from the spectral problem compose a Lie algebra. By considering its infinite dimensional subalgebras and continuum limit of recursion operator, three semi-discrete AKNS hierarchies are constructed.

nlin.SI↗
arXiv2008

Surface Generation Analysis in Micro End-Milling Considering the Influences of Grain

Micro end-milling method is a universal micro manufacturing method, which can be used to fabricating complex 3D structures and parts with many materials. But compared with their micrometer order size, their surface roughness quality is not satisfied. In this paper, the different metal phase grains influences are researched, and the micro end-milling process is described while the material is anisotropic. In this paper, the physical characteristics of different grains, especially friction coefficient and elastic module, are very critical to determine the chip formation process and surface generation. The chip is often discontinues because of the grain boundary effect. Through the micro end-milling experiment, the bottom surface results correlate very well with the theory analysis.

cs.OH↗