arXiv subjects

Kexin Ding

Publications and source records attributed to Kexin Ding.

10 recordsLinked to original sources

arXiv2026

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications. Consequently, the field is undergoing an emerging paradigm shift from isolated skill creation to automated, evaluation-driven skill evolution. In this survey, we systematically examine the landscape of skill evolution and evaluation beyond foundational skill creation. We categorize evolution into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, showing how each element contributes to improving skill utility and reliability. We also provide an analysis of six skill-centric benchmark categories, identifying structural gaps in benchmark coverage, trade-offs, and metric richness to advance skill research. Finally, we identify open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe. The project URL is https://github.com/Cassie07/AgentSkill_Survey

cs.CL↗

arXiv2025

Chip-Firing Games on Banana Trees

We study chip-firing games on multigraphs whose underlying simple graphs are trees, paths, and stars, denoted as banana trees, paths, and stars respectively. We present a polynomial time algorithm to compute the divisorial gonality of banana paths, and give combinatorial formulas for the related invariants of scramble number and screewidth for any banana tree. Furthermore, we leverage banana paths to show that gonality can increase or decrease by an arbitrary amount upon deletion of a single edge, even when the resulting graph is connected. Lastly, we study banana trees and Brill-Noether theory to prove that the gonality conjecture holds for all banana trees.

math.CO↗

arXiv2025

Aligning Large Language Models with Healthcare Stakeholders: A Pathway to Trustworthy AI Integration

The wide exploration of large language models (LLMs) raises the awareness of alignment between healthcare stakeholder preferences and model outputs. This alignment becomes a crucial foundation to empower the healthcare workflow effectively, safely, and responsibly. Yet the varying behaviors of LLMs may not always match with healthcare stakeholders' knowledge, demands, and values. To enable a human-AI alignment, healthcare stakeholders will need to perform essential roles in guiding and enhancing the performance of LLMs. Human professionals must participate in the entire life cycle of adopting LLM in healthcare, including training data curation, model training, and inference. In this review, we discuss the approaches, tools, and applications of alignments between healthcare stakeholders and LLMs. We demonstrate that LLMs can better follow human values by properly enhancing healthcare knowledge integration, task understanding, and human guidance. We provide outlooks on enhancing the alignment between humans and LLMs to build trustworthy real-world healthcare applications.

cs.CY↗

arXiv2025

MedForge: Building Medical Foundation Models Like Open Source Software Development

Foundational models (FMs) have made significant strides in the healthcare domain. Yet the data silo challenge and privacy concern remain in healthcare systems, hindering safe medical data sharing and collaborative model development among institutions. The collection and curation of scalable clinical datasets increasingly become the bottleneck for training strong FMs. In this study, we propose Medical Foundation Models Merging (MedForge), a cooperative framework enabling a community-driven medical foundation model development, meanwhile preventing the information leakage of raw patient data and mitigating synchronization model development issues across clinical institutions. MedForge offers a bottom-up model construction mechanism by flexibly merging task-specific Low-Rank Adaptation (LoRA) modules, which can adapt to downstream tasks while retaining original model parameters. Through an asynchronous LoRA module integration scheme, the resulting composite model can progressively enhance its comprehensive performance on various clinical tasks. MedForge shows strong performance on multiple clinical datasets (e.g., breast cancer, lung cancer, and colon cancer) collected from different institutions. Our major findings highlight the value of collaborative foundation models in advancing multi-center clinical collaboration effectively and cohesively. Our code is publicly available at https://github.com/TanZheling/MedForge.

cs.LG↗

arXiv2024

Chip-firing on the Platonic solids: a primer for studying graph gonality

This paper provides a friendly introduction to chip-firing games and graph gonality. We use graphs coming from the five Platonic solids to illustrate different tools and techniques for studying these games, including independent sets, treewidth, scramble number, and Dhar's burning algorithm. In addition to showcasing some previously known results, we present the first proofs that the dodecahedron graph has gonality $6$, and that the icosahedron graph has gonality~$9$.

math.AG↗

arXiv2024

The gonality of chess graphs

Chess graphs encode the moves that a particular chess piece can make on an $m\times n$ chessboard. We study through these graphs through the lens of chip-firing games and graph gonality. We provide upper and lower bounds for the gonality of king's, bishop's, and knight's graphs, as well as for the toroidal versions of these graphs. We also prove that among all chess graphs, there exists an upper bound on gonality solely in terms of $\min\{m,n\}$, except for queen's, toroidal queen's, rook's, and toroidal bishop's graphs.

math.CO↗

arXiv2024

Data-Centric Foundation Models in Computational Healthcare: A Survey

The advent of foundation models (FMs) as an emerging suite of AI techniques has struck a wave of opportunities in computational healthcare. The interactive nature of these models, guided by pre-training data and human instructions, has ignited a data-centric AI paradigm that emphasizes better data characterization, quality, and scale. In healthcare AI, obtaining and processing high-quality clinical data records has been a longstanding challenge, encompassing data quantity, annotation, patient privacy, and ethics. In this survey, we investigate a wide range of data-centric approaches in the FM era (from model pre-training to inference) towards improving the healthcare workflow. We discuss key perspectives in AI security, assessment, and alignment with human values. Finally, we offer a promising outlook on FM-based analytics to enhance patient outcomes and clinical workflows in the evolving landscape of healthcare and medicine. We provide an up-to-date list of healthcare-related foundation models and datasets at https://github.com/Yunkun-Zhang/Data-Centric-FM-Healthcare.

cs.LG↗

arXiv2023

Statistical Inference on Grayscale Images via the Euler-Radon Transform

Tools from topological data analysis have been widely used to represent binary images in many scientific applications. Methods that aim to represent grayscale images (i.e., where pixel intensities instead take on continuous values) have been relatively underdeveloped. In this paper, we introduce the Euler-Radon transform, which generalizes the Euler characteristic transform to grayscale images by using o-minimal structures and Euler integration over definable functions. Coupling the Karhunen-Loeve expansion with our proposed topological representation, we offer hypothesis-testing algorithms based on the chi-squared distribution for detecting significant differences between two groups of grayscale images. We illustrate our framework via extensive numerical experiments and simulations.

stat.ME↗

arXiv2023

Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction

Survival outcome assessment is challenging and inherently associated with multiple clinical factors (e.g., imaging and genomics biomarkers) in cancer. Enabling multimodal analytics promises to reveal novel predictive patterns of patient outcomes. In this study, we propose a multimodal transformer (PathOmics) integrating pathology and genomics insights into colon-related cancer survival prediction. We emphasize the unsupervised pretraining to capture the intrinsic interaction between tissue microenvironments in gigapixel whole slide images (WSIs) and a wide range of genomics data (e.g., mRNA-sequence, copy number variant, and methylation). After the multimodal knowledge aggregation in pretraining, our task-specific model finetuning could expand the scope of data utility applicable to both multi- and single-modal data (e.g., image- or genomics-only). We evaluate our approach on both TCGA colon and rectum cancer cohorts, showing that the proposed approach is competitive and outperforms state-of-the-art studies. Finally, our approach is desirable to utilize the limited number of finetuned samples towards data-efficient analytics for survival outcome prediction. The code is available at https://github.com/Cassie07/PathOmics.

cs.CV↗

arXiv2022

Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applications

Image-based characterization and disease understanding involve integrative analysis of morphological, spatial, and topological information across biological scales. The development of graph convolutional networks (GCNs) has created the opportunity to address this information complexity via graph-driven architectures, since GCNs can perform feature aggregation, interaction, and reasoning with remarkable flexibility and efficiency. These GCNs capabilities have spawned a new wave of research in medical imaging analysis with the overarching goal of improving quantitative disease understanding, monitoring, and diagnosis. Yet daunting challenges remain for designing the important image-to-graph transformation for multi-modality medical imaging and gaining insights into model interpretation and enhanced clinical decision support. In this review, we present recent GCNs developments in the context of medical image analysis including imaging data from radiology and histopathology. We discuss the fast-growing use of graph network architectures in medical image analysis to improve disease diagnosis and patient outcomes in clinical practice. To foster cross-disciplinary research, we present GCNs technical advancements, emerging medical applications, identify common challenges in the use of image-based GCNs and their extensions in model interpretation, large-scale benchmarks that promise to transform the scope of medical image studies and related graph-driven medical research.

eess.IV↗