Author name cluster

Xinyu Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion

Tong Chen
Xinyu Ma
Long Bai
Wenyang Wang
Yue Sun
Luping Zhou

Endoscopic images often suffer from diverse and co-occurring degradations such as low lighting, smoke, and bleeding, which obscure critical clinical details. Existing restoration methods are typically task-specific and often require prior knowledge of the degradation type, limiting their robustness in real-world clinical use. We propose EndoIR, an all-in-one, degradation-agnostic diffusion-based framework that restores multiple degradation types using a single model. EndoIR introduces a Dual-Domain Prompter that extracts joint spatial–frequency features, coupled with an adaptive embedding that encodes both shared and task-specific cues as conditioning for denoising. To mitigate feature confusion in conventional concatenation-based conditioning, we design a Dual-Stream Diffusion architecture that processes clean and degraded inputs separately, with a Rectified Fusion Block integrating them in a structured, degradation-aware manner. Furthermore, Noise-Aware Routing Block improves efficiency by dynamically selecting only noise-relevant features during denoising. Experiments on SegSTRONG-C and CEC datasets demonstrate that EndoIR achieves state-of-the-art performance across multiple degradation scenarios while using fewer parameters than strong baselines, and downstream segmentation experiments confirm its clinical utility.

PDF Details DOI

ICLR Conference 2025 Conference Paper

DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing

Xinyu Ma
Yifeng Xu
Yang Lin
Tianlong Wang
Xu Chu
Xin Gao
Junfeng Zhao 0001
Yasha Wang

We introduce DRESS, a novel approach for generating stylized large language model (LLM) responses through representation editing. Existing methods like prompting and fine-tuning are either insufficient for complex style adaptation or computationally expensive, particularly in tasks like NPC creation or character role-playing. Our approach leverages the over-parameterized nature of LLMs to disentangle a style-relevant subspace within the model's representation space to conduct representation editing, ensuring a minimal impact on the original semantics. By applying adaptive editing strengths, we dynamically adjust the steering vectors in the style subspace to maintain both stylistic fidelity and semantic integrity. We develop two stylized QA benchmark datasets to validate the effectiveness of DRESS, and the results demonstrate significant improvements compared to baseline methods such as prompting and ITI. In short, DRESS is a lightweight, train-free solution for enhancing LLMs with flexible and effective style control, making it particularly useful for developing stylized conversational agents. Codes and benchmark datasets are available at https://github.com/ArthurLeoM/DRESS-LLM.

Details

NeurIPS Conference 2025 Conference Paper

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

Yiqun Chen
Lingyong Yan
Weiwei Sun
Xinyu Ma
Yi Zhang
Shuaiqiang Wang
Dawei Yin
Yiming Yang

Retrieval-augmented generation (RAG) is widely utilized to incorporate external knowledge into large language models, thereby enhancing factuality and reducing hallucinations in question-answering (QA) tasks. A standard RAG pipeline consists of several components, such as query rewriting, document retrieval, document filtering, and answer generation. However, these components are typically optimized separately through supervised fine-tuning, which can lead to misalignments between the objectives of individual components and the overarching aim of generating accurate answers. Although recent efforts have explored using reinforcement learning (RL) to optimize specific RAG components, these approaches often focus on simple pipelines with only two components or do not adequately address the complex interdependencies and collaborative interactions among the modules. To overcome these limitations, we propose treating the complex RAG pipeline with multiple components as a multi-agent cooperative task, in which each component can be regarded as an RL agent. Specifically, we present MMOA-RAG\footnote{The code of MMOA-RAG is on \url{https: //github. com/chenyiqun/MMOA-RAG}. }, \textbf{M}ulti-\textbf{M}odule joint \textbf{O}ptimization \textbf{A}lgorithm for \textbf{RAG}, which employs multi-agent reinforcement learning to harmonize all agents' goals toward a unified reward, such as the F1 score of the final answer. Experiments conducted on various QA benchmarks demonstrate that MMOA-RAG effectively boost the overall performance of the pipeline and outperforms existing baselines. Furthermore, comprehensive ablation studies validate the contributions of individual components and demonstrate MMOA-RAG can be adapted to different RAG pipelines and benchmarks.

PDF Details

ICML Conference 2024 Conference Paper

Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation

Xinyu Ma
Xu Chu
Zhibang Yang
Yang Lin
Xin Gao
Junfeng Zhao 0001

With the increasingly powerful performances and enormous scales of pretrained models, promoting parameter efficiency in fine-tuning has become a crucial need for effective and efficient adaptation to various downstream tasks. One representative line of fine-tuning methods is Orthogonal Fine-tuning (OFT), which rigorously preserves the angular distances within the parameter space to preserve the pretrained knowledge. Despite the empirical effectiveness, OFT still suffers low parameter efficiency at $\mathcal{O}(d^2)$ and limited capability of downstream adaptation. Inspired by Givens rotation, in this paper, we proposed quasi-Givens Orthogonal Fine-Tuning (qGOFT) to address the problems. We first use $\mathcal{O}(d)$ Givens rotations to accomplish arbitrary orthogonal transformation in $SO(d)$ with provable equivalence, reducing parameter complexity from $\mathcal{O}(d^2)$ to $\mathcal{O}(d)$. Then we introduce flexible norm and relative angular adjustments under soft orthogonality regularization to enhance the adaptation capability of downstream semantic deviations. Extensive experiments on various tasks and pretrained models validate the effectiveness of our methods.

Details

NeurIPS Conference 2023 Conference Paper

Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications

Xinyu Ma
Xu Chu
Yasha Wang
Yang Lin
Junfeng Zhao
Liantao Ma
Wenwu Zhu

Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals. To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a "midpoint" of source graphs in the Fused Gromov-Wasserstein (FGW) metric space. To enhance the scalability of our method, we introduce a relaxed FGW solver that accelerates FGWMixup by improving the convergence rate from $\mathcal{O}(t^{-1})$ to $\mathcal{O}(t^{-2})$. Extensive experiments conducted on five datasets using both classic (MPNNs) and advanced (Graphormers) GNN backbones demonstrate that \mname\xspace effectively improves the generalizability and robustness of GNNs. Codes are available at https: //github. com/ArthurLeoM/FGWMixup.

PDF Details

TCS Journal 2021 Journal Article

Subnetwork reliability analysis of bubble-sort graph networks

Kai Feng
Xinyu Ma
Wei Wei

The bubble-sort graph network B n is recognized as an attractive interconnection network topology for building multiprocessor computer systems. In this paper, the subnetwork reliability of B n is analyzed in the presence of node failures. An upper bound and a lower bound on the B n − 1 subnetwork reliability of B n are established under the probability fault model, and the theoretical results are proved to be in accordance with and near to the simulation results. Moreover, under the node fault model, the mean time to failure to maintain the fault-free status of different number of disjoint B n − 1 subnetworks in B n is evaluated by using the fixed partitioning and the flexible partitioning, respectively, and it is shown that B n has better robustness under the flexible partitioning pattern when disjoint B n − 1 subnetworks need to be used.

Details DOI

AAAI Conference 2020 Conference Paper

AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration

Liantao Ma
Junyi Gao
Yasha Wang
Chaohe Zhang
Jiangtao Wang
Wenjie Ruan
Wen Tang
Xin Gao

Deep learning-based health status representation learning and clinical prediction have raised much research interest in recent years. Existing models have shown superior performance, but there are still several major issues that have not been fully taken into consideration. First, the historical variation pattern of the biomarker in diverse time scales plays a vital role in indicating the health status, but it has not been explicitly extracted by existing works. Second, key factors that strongly indicate the health risk are different among patients. It is still challenging to adaptively make use of the features for patients in diverse conditions. Third, using prediction models as the black box will limit the reliability in clinical practice. However, none of the existing works can provide satisfying interpretability and meanwhile achieve high prediction performance. In this work, we develop a general health status representation learning model, named AdaCare. It can capture the long and short-term variations of biomarkers as clinical features to depict the health status in multiple time scales. It also models the correlation between clinical features to enhance the ones which strongly indicate the health status and thus can maintain a state-of-the-art performance in terms of prediction accuracy while providing qualitative interpretability. We conduct a health risk prediction experiment on two real-world datasets. Experiment results indicate that AdaCare outperforms state-of-the-art approaches and provides effective interpretability, which is veriﬁable by clinical experts.

PDF Details

AAAI Conference 2020 Conference Paper

ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context

Liantao Ma
Chaohe Zhang
Yasha Wang
Wenjie Ruan
Jiangtao Wang
Wen Tang
Xinyu Ma
Xin Gao

Predicting the patient’s clinical outcome from the historical electronic medical records (EMR) is a fundamental research problem in medical informatics. Most deep learning-based solutions for EMR analysis concentrate on learning the clinical visit embedding and exploring the relations between visits. Although those works have shown superior performances in healthcare prediction, they fail to explore the personal characteristics during the clinical visits thoroughly. Moreover, existing works usually assume that the more recent record weights more in the prediction, but this assumption is not suitable for all conditions. In this paper, we propose ConCare to handle the irregular EMR data and extract feature interrelationship to perform individualized healthcare prediction. Our solution can embed the feature sequences separately by modeling the time-aware distribution. ConCare further improves the multi-head self-attention via the cross-head decorrelation, so that the inter-dependencies among dynamic features and static baseline information can be effectively captured to form the personal health context. Experimental results on two real-world EMR datasets demonstrate the effectiveness of ConCare. The medical ﬁndings extracted by ConCare are also empirically conﬁrmed by human experts and medical literature.

PDF Details