Author name cluster

Xinyi Liu

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.

6 papers

2 author rows

AAAI Conference 2026 Conference Paper

OncoCoT: A Temporal-causal Chain-of-Thought Dataset for Oncologic Decision-Making

Peiru Yang
Yudong Li
Shiting Wang
Xinyi Liu
Haotian Gan
Xintian Li
Qingyu Gao
Yongfeng Huang

Long Chain-of-Thought (CoT) reasoning has shown great promise in complex reasoning tasks, but its application to medical decision-making presents unique challenges. Unlike structured tasks relying on static verification frameworks, medical decision-making requires dynamic validation through longitudinal clinical outcomes, exhibiting temporal-causal dependencies that complicate the verification of reasoning processes. Therefore, we introduce a novel data construction framework specifically designed for medical decision-making. First, the framework analyzes real-world clinical cases to construct a timeline of medical events and identify critical decision points, including examination, diagnosis, and treatment. Subsequently, it employs a clinical causality-aware strategy to generate decision-making questions at the identified points, along with reasoning traces and corresponding answers. Finally, information drawn from future nodes serves as clinical logic-constrained criteria to re-evaluate and refine the soundness of the generated reasoning and responses. Building on this, we present OncoCoT, an oncologic decision-making dataset derived from clinical records over the past four years across eight common cancer types. Furthermore, we distill a subset of OncoCoT into a dedicated benchmark, OncoEval, to facilitate systematic evaluation of clinical reasoning capabilities in LLMs. Evaluation results show that existing state-of-the-art reasoning models, such as Deepseek-r1 and GPT-o3, exhibit limited capability in addressing clinical problems in OncoEval, highlighting the need for further improvement.

PDF Details DOI

AAAI Conference 2026 Conference Paper

ShieldRAG: Safeguarding Retrieval-Augmented Generation from Untrusted Knowledge Bases

Peiru Yang
Haoran Zheng
Yi Luo
Xinyi Liu
Jinrui Wang
Huili Wang
Xintian Li
Yongfeng Huang

Open knowledge bases (e.g., websites) are widely adopted in Retrieval-Augmented Generation (RAG) systems to provide supplementary knowledge (e.g., latest information). However, such sources inevitably contain biased or harmful content, and incorporating these untrusted contents into the RAG process introduces significant safety risks, including the degradation of LLM performance and the potential generation of harmful outputs. Recent studies have shown that this vulnerability can be further amplified by adversarial poisoning attacks specifically targeting the knowledge sources. Most existing methods primarily emphasize improving the accuracy and efficiency of RAG systems, usually overlooking these critical safety concerns. In this paper, we propose a safety-aware retrieval framework (ShieldRAG) designed to augment language model generation by jointly optimizing for both relevance and safety in the retrieved knowledge content. The core idea of ShieldRAG is to transfer the safety knowledge implicitly encoded in powerful LLMs into the retriever model through an adversarial knowledge alignment mechanism. This can empower the retriever with the safety awareness, and adapt to the diverse and unknown distribution of unsafe content encountered in practical scenarios. We evaluate ShieldRAG on seven real-world datasets using five widely-used LLMs and two state-of-the-art poisoning attack strategies. Experimental results show that our method substantially improves the robustness of RAG systems against unsafe knowledge sources, while maintaining competitive performance in terms of generation accuracy and efficiency.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images

Xuejun Huang
Xinyi Liu
Yi Wan
Zhi Zheng
Bin Zhang
Mingtao Xiong
Yingying Pei
Yongjun Zhang

Three-dimensional scene reconstruction from sparse-view satellite images is a long-standing and challenging task. While 3D Gaussian Splatting (3DGS) and its variants have recently attracted attention for its high efficiency, existing methods remain unsuitable for satellite images due to incompatibility with rational polynomial coefficient (RPC) models and limited generalization capability. Recent advances in generalizable 3DGS approaches show potential, but they perform poorly on multi-temporal sparse satellite images due to limited geometric constraints, transient objects, and radiometric inconsistencies. To address these limitations, we propose SkySplat, a novel self-supervised framework that integrates the RPC model into the generalizable 3DGS pipeline, enabling more effective use of sparse geometric cues for improved reconstruction. SkySplat relies only on RGB images and radiometric-robust relative height supervision, thereby eliminating the need for ground-truth height maps. Key components include a Cross-Self Consistency Module (CSCM), which mitigates transient object interference via consistency-based masking, and a multi-view consistency aggregation strategy that refines reconstruction results. Compared to per-scene optimization methods, SkySplat achieves an 86 times speedup over EOGS with higher accuracy. It also outperforms generalizable 3DGS baselines, reducing MAE from 13.18 m to 1.80 m on the DFC19 dataset significantly, and demonstrates strong cross-dataset generalization on the MVS3D benchmark.

PDF Details DOI

ICLR Conference 2025 Conference Paper

NetMoE: Accelerating MoE Training through Dynamic Sample Placement

Xinyi Liu
Yujie Wang
Fangcheng Fu
Xupeng Miao
Shenhan Zhu
Xiaonan Nie
Bin Cui 0001

Mixture of Experts (MoE) is a widely used technique to expand model sizes for better model quality while maintaining the computation cost constant. In a nutshell, an MoE model consists of multiple experts in each model layer and routes the training tokens to only a fixed number of experts rather than all. In distributed training, as experts are distributed among different GPUs, All-to-All communication is necessary to exchange the training tokens among the GPUs after each time of expert routing. Due to the frequent and voluminous data exchanges, All-to-All communication has become a notable challenge to training efficiency. In this paper, we manage to accelerate All-to-All communication in MoE models from the training sample perspective, which is unexplored so far. In particular, we put forward the observation that tokens in the same training sample have certain levels of locality in expert routing. Motivated by this, we develop NetMoE, which takes such locality into account and dynamically rearranges the placement of training samples to minimize All-to-All communication costs. Specifically, we model the All-to-All communication given the sample placement and formulate an integer programming problem to deduce the optimal placement in polynomial time. Experiments with 32 GPUs show that NetMoE achieves a maximum efficiency improvement of $1.67 \times$ compared with current MoE training frameworks.

Details

ICRA Conference 2024 Conference Paper

Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration

Jinning Li 0002
Xinyi Liu
Banghua Zhu
Jiantao Jiao
Masayoshi Tomizuka
Chen Tang 0001
Wei Zhan

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the overall performance. In many realistic tasks, e. g. autonomous driving, large-scale expert demonstration data are available. We argue that extracting expert policy from offline data to guide online exploration is a promising solution to mitigate the conserveness issue. Large-capacity models, e. g. decision transformers (DT), have been proven to be competent in offline policy learning. However, data collected in realworld scenarios rarely contain dangerous cases (e. g. , collisions), which makes it prohibitive for the policies to learn safety concepts. Besides, these bulk policy networks cannot meet the computation speed requirements at inference time on real-world tasks such as autonomous driving. To this end, we propose Guided Online Distillation (GOLD), an offline-to-online safe RL framework. GOLD distills an offline DT policy into a lightweight policy network through guided online safe RL training, which outperforms both the offline DT policy and online safe RL algorithms. Experiments in both benchmark safe RL tasks and real-world driving tasks based on the Waymo Open Motion Dataset (WOMD) [1] demonstrate that GOLD can successfully distill lightweight policies and solve decision-making problems in challenging safety-critical scenarios.

Details

YNIMG Journal 2021 Journal Article

Identification of microRNA-9 linking the effects of childhood maltreatment on depression using amygdala connectivity

Cancan He
Ying Bai
Zan Wang
Dandan Fan
Qing Wang
Xinyi Liu
Haisan Zhang
Hongxing Zhang

Childhood maltreatment (CM) is regarded as an important risk factor for major depressive disorder (MDD). However, the neural links corresponding to the process of early CM experience producing brain alterations and then leading to depression later remain unclear. To explore the neural basis of the effects of CM on MDD and the potential role of microRNA-9 (miR-9) in these processes, we recruited 40 unmedicated MDD patients and 34 healthy controls (HCs) to complete resting-state fMRI scans and peripheral blood miR-9 tests. The neural substrates of CM, miR-9, and depression, as well as their interactive effects on intrinsic amygdala functional connectivity (AFC) networks were investigated in MDD patients. Two-step mediation analysis was separately employed to explore whether AFC strength mediates the association among CM severity, miR-9 levels, and depression. A support vector classifier (SVC) model of machine learning was used to distinguish MDD patients from HCs. MDD patients showed higher miR-9 levels that were negatively correlated with CM scores and depressive severity. Overlapping effects of CM, miR-9, and depressive severity on bilateral AFC networks in MDD patients were primarily located in the prefrontal-striatum pathway and limbic system. The connection of amygdala to prefrontal-limbic circuits could mediate the effects of CM severity on the miR-9 levels, as well as the impacts of miR-9 levels on the severity of depression in MDD patients. Furthermore, the SVC model, which integrated miR-9 levels, CM severity, and AFC strength in prefrontal-limbic regions, had good power in differentiating MDD patients from HCs (accuracy 85.1%). MiR-9 may play a crucial role in the process of CM experience-produced brain changes targeting prefrontal-limbic regions and that subsequently leads to depression. The present neuroimaging-epigenetic results provide new insight into our understanding of MDD pathophysiology.

Details DOI