Author name cluster

Yu Xing

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.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

EchoEdit: Consistent Multi-Hop Question Answering via Ripple Control in Knowledge Editing

Jinwei Shi
Wenxuan Huang
Yu Xing
Yunhui Liu
Tao Zheng
Bin Chong
Tieke He

Knowledge editing aims to update specific knowledge in Large Language Models (LLMs) without retraining the entire model. However, existing methods generally struggle to manage the ripple effects of knowledge updates, particularly in multi-hop reasoning tasks, where conflicts between old and new information often lead to shifts in reasoning chains and degraded consistency. To address this issue, a ripple-aware knowledge editing framework, namely EchoEdit, is proposed. EchoEdit introduces the RippleGraph to explicitly model potentially affected knowledge regions and employs a RippleRule generator to dynamically produce diffusion rules, precisely constraining knowledge propagation. Furthermore, we distill a Chain-of-Thought (CoT) planner from an external teacher model, which decouples complex reasoning chain planning into RippleGraph-guided reasoning, thereby alleviating the reasoning burden on low-resource LLMs in multi-hop tasks. Experimental results on the MQuAKE and RIPPLEEDITS multi-hop reasoning benchmarks demonstrate that EchoEdit significantly outperforms existing mainstream methods, effectively enhancing post-edit reasoning consistency and generalization capabilities.

PDF Details DOI

AAAI Conference 2026 Conference Paper

On Modality Weighting and Specificity for Multi-Modal Entity Alignment

Yu Xing
Qizhuo Xie
Yunhui Liu
Qing Gu
Tao Zheng
Bin Chong
Tieke He

Multi-modal entity alignment aims to identify equivalent entities across different multi-modal knowledge graphs (MMKGs). While prior work has achieved notable progress through improved multi-modal encoding and cross-modal fusion techniques, two critical challenges remain unresolved. First, due to the heterogeneous and often inconsistent sources from which MMKGs are constructed, the quality and informativeness of modalities vary significantly across entities, leading to the modality weighting problem. Second, existing cross-modal fusion mechanisms predominantly emphasize modality-shared information, often at the expense of modality-specific signals that are also essential for precise alignment. To address these issues, we propose HUMEA, a novel framework that integrates hierarchical Mixture-of-Experts (MoE) with unimodal distillation. HUMEA consists of: (1) A hierarchical MoE module comprising intra-modal and inter-modal experts, which adaptively modulates modality contributions by capturing entity representations at fine-to-coarse semantic granularities. In addition, we introduce a contrastive mutual information loss to enhance expert diversity and reduce redundancy. (2) A unimodal distillation strategy that preserves modality-specific information in the fused representations through single-modality alignment and distillation, achieving a balanced integration of shared and unique modality features. Extensive experiments on two benchmark datasets, FB15K-DB15K and FB15K-YAGO15K, demonstrate state-of-the-art performance, validating the effectiveness of our approach.

PDF Details DOI

IROS Conference 2025 Conference Paper

Ultra-Wideband assisted Visual-Inertial Localization Correction System with Position-Unknown UWB Anchors

Yu Xing
Weixing Li
Feng Pan
Xiaoxue Feng

Given the fact that visual-inertial odometry (VIO) is faced with the challenges of localization drift in the long run, we utilize drift-free Ultra-Wideband (UWB) measurements to eliminate accumulated errors in VIO. Existing UWB-VIO fusion methods are mostly constrained by the accuracy of prior UWB anchor positions. However, in large-scale localization scenarios, the precise locations of UWB anchors are difficult to obtain, and the offline calibration process is complex, significantly limiting flexibility. In this paper, we firstly design a lightweight initialization method based on a dual sliding window structure, which can rapidly obtain initial guesses for the UWB anchor coordinates. After that, we further propose a joint estimation system to refine the anchor coordinates while estimating the correction for VIO. The system combines filter-based and optimization-based methods, which mainly consists of an initialization module and a nonlinear estimator module. The filter in the initialization module provides optimization initial values and covariances, and mutually, the optimization results from the nonlinear estimator provide priors for the filter. Finally, the performance of our proposed approach is verified through both public datasets and real-world experiment. Our project, along with our dataset, has been open-sourced in the form of ROS package and ROS bag.

Details

ICLR Conference 2022 Conference Paper

On the Convergence of mSGD and AdaGrad for Stochastic Optimization

Ruinan Jin
Yu Xing
Xingkang He

As one of the most fundamental stochastic optimization algorithms, stochastic gradient descent (SGD) has been intensively developed and extensively applied in machine learning in the past decade. There have been some modified SGD-type algorithms, which outperform the SGD in many competitions and applications in terms of convergence rate and accuracy, such as momentum-based SGD (mSGD) and adaptive gradient algorithm (AdaGrad). Despite these empirical successes, the theoretical properties of these algorithms have not been well established due to technical difficulties. With this motivation, we focus on convergence analysis of mSGD and AdaGrad for any smooth (possibly non-convex) loss functions in stochastic optimization. First, we prove that the iterates of mSGD are asymptotically convergent to a connected set of stationary points with probability one, which is more general than existing works on subsequence convergence or convergence of time averages. Moreover, we prove that the loss function of mSGD decays at a certain rate faster than that of SGD. In addition, we prove the iterates of AdaGrad are asymptotically convergent to a connected set of stationary points with probability one. Also, this result extends the results from the literature on subsequence convergence and the convergence of time averages. Despite the generality of the above convergence results, we have relaxed some assumptions of gradient noises, convexity of loss functions, as well as boundedness of iterates.

Details

IJCAI Conference 2019 Conference Paper

Hi-Fi Ark: Deep User Representation via High-Fidelity Archive Network

Zheng Liu
Yu Xing
Fangzhao Wu
Mingxiao An
Xing Xie

Deep learning techniques have been widely applied to modern recommendation systems, bringing in flexible and effective ways of user representation. Conventionally, user representations are generated purely in the offline stage. Without referencing to the specific candidate item for recommendation, it is difficult to fully capture user preference from the perspective of interest. More recent algorithms tend to generate user representation at runtime, where user's historical behaviors are attentively summarized w. r. t. the presented candidate item. In spite of the improved efficacy, it is too expensive for many real-world scenarios because of the repetitive access to user's entire history. In this work, a novel user representation framework, Hi-Fi Ark, is proposed. With Hi-Fi Ark, user history is summarized into highly compact and complementary vectors in the offline stage, known as archives. Meanwhile, user preference towards a specific candidate item can be precisely captured via the attentive aggregation of such archives. As a result, both deployment feasibility and superior recommendation efficacy are achieved by Hi-Fi Ark. The effectiveness of Hi-Fi Ark is empirically validated on three real-world datasets, where remarkable and consistent improvements are made over a variety of well-recognized baseline methods.

PDF Details