Xiao Xu

Xiao Xu

Auto-generated profile, based on publicly available information

Xiao Xu

Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, Heilongjiang, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 October 2020 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
GGGuibing Guo
Guibing Guo
HZHuan Zhou
Huan Zhou
BCBowei Chen
Bowei Chen
ZLZhirong Liu
Zhirong Liu
XXXiao Xu
Xiao Xu
XHXiuqiang He
Xiuqiang He
Negative sampling plays an important role in ranking-based recommender models. However, most existing sampling methods cannot generate informative item pairs with positive and negative instances due to two limitations: 1) they merely treat observed items as positive instances, ignoring the existence of potential positive items (i.e., nonobserved items users may prefer) and the probability of observed but noisy items and 2) they fail to capture the relationship between positive and negative items during negative sampling, which may cause the unexpected selection of potential positive items. In this article, we introduce a dynamic sampling strategy to search informative item pairs. Specifically, we first sample a positive instance from all the items by leveraging the overall features of user's observed items. Then, we strategically select a negative instance by considering its correlation with the sampled positive one. Formally, we propose an item pair generative adversarial network named IPGAN, where our sampling strategy is realized in two generative models for positive and negative instances, respectively. In addition, IPGAN can also ensure that the sampled item pairs are informative relative to the ground truth by a discriminative model. What is more, we propose a batch-training approach to further enhance both user and item modeling by alleviating the special bias (noise) from different users. This approach can also significantly accelerate the process of model training compared with classical GAN method for recommendation. Experimental results on three real data sets show that our approach outperforms other state-of-the-art approaches in terms of recommendation accuracy.

17 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
LQLibo Qin
Libo Qin
XXXiao Xu
Xiao Xu
WCWanxiang Che
Wanxiang Che
TLTing Liu
Ting Liu
In real-world scenarios, users usually have multiple intents in the same utterance. Unfortunately, most spoken language understanding (SLU) models either mainly focused on the single intent scenario, or simply incorporated an overall intent context vector for all tokens, ignoring the fine-grained multiple intents information integration for token-level slot prediction. In this paper, we propose an Adaptive Graph-Interactive Framework (AGIF) for joint multiple intent detection and slot filling, where we introduce an intent-slot graph interaction layer to model the strong correlation between the slot and intents. Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information, making a fine-grained intent information integration for the token-level slot prediction. Experimental results on three multi-intent datasets show that our framework obtains substantial improvement and achieves the state-of-the-art performance. In addition, our framework achieves new state-of-the-art performance on two single-intent datasets.

9 June 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XXXiao Xu
Xiao Xu
LQLibo Qin
Libo Qin
WCWanxiang Che
Wanxiang Che
MKMin-Yen Kan
Min-Yen Kan
Two-Tower Vision–Language Models (VLMs) have demonstrated strong performance across various downstream VL tasks. While BridgeTower further enhances performance by building bridges between encoders, it (i) suffers from ineffective layer-by-layer utilization of unimodal representations, (ii) restricts the flexible exploitation of different levels of unimodal semantic knowledge, and (iii) is limited to the evaluation on traditional low-resolution datasets only with the Two-Tower VLM architecture. In this work, we propose Manager, a lightweight, efficient and effective plugin that adaptively aggregates insights from different levels of pre-trained unimodal experts to facilitate more comprehensive VL alignment and fusion. First, under the Two-Tower VLM architecture, we introduce ManagerTower, a novel VLM that introduces the manager in each cross-modal layer. Whether with or without VL pre-training, ManagerTower outperforms previous strong baselines and achieves superior performance on 4 downstream VL tasks. Moreover, we extend our exploration to the latest Multimodal Large Language Model (MLLM) architecture.We demonstrate that LLaVA-OV-Manager significantly boosts the zero-shot performance of LLaVA-OV across different categories of capabilities, images, and resolutions on 20 downstream datasets, whether the multi-grid algorithm is enabled or not. In-depth analysis reveals that both our manager and the multi-grid algorithm can be viewed as a plugin that improves the visual representation by capturing more diverse visual details from two orthogonal perspectives (depth and width). Their synergy can mitigate the semantic ambiguity caused by the multi-grid algorithm and further improve performance. Code and models are available at https://github.com/LooperXX/ManagerTower.


31 March 2023
Verified
Other
Open access
WXWanhong Xu
Wanhong Xu
BXBiao Xi
Biao Xi
JWJieying Wu
Jieying Wu
HAHaoyun (Harry) An
Haoyun (Harry) An
JZJenny Zhu
Jenny Zhu
XXXiao Xu
Xiao Xu
Bis(4-fluorobenzyl)trisulfide (BFBTS) is a synthetic molecule derived from a bioactive natural product, dibenzyltrisulfide, found in a subtropical shrub, Petiveria allieacea. BFBTS has potent anticancer activities to a broad spectrum of tumor cell lines with IC50 values from high nanomolar to low micromolar and showed equal anticancer potency between tumor cell lines overexpressing multidrug-resistant gene, MDR1 (MCF7/adr line and KBv200 line), and their parental MCF7 line and KB lines. BFBTS inhibited microtubule polymerization dynamics in MCF7 cells, at a low nanomolar concentration of 54 nmol/L, while disrupting microtubule filaments in cells at low micromolar concentration of 1 μmol/L. Tumor cells treated with BFBTS were arrested at G2-M phase, conceivably resulting from BFBTS-mediated antimicrotubule activities. Mass spectrometry studies revealed that BFBTS bound and modified β-tubulin at residue Cys12, forming β-tubulin-SS-fluorobenzyl. The binding site differs from known antimicrotubule agents, suggesting that BFBTS functions as a novel antimicrotubule agent. BFBTS at a dose of 25 mg/kg inhibited tumor growth with relative tumor growth rates of 19.91%, 18.5%, and 23.42% in A549 lung cancer, Bcap-37 breast cancer, and SKOV3 ovarian cancer xenografts, respectively. Notably, BFBTS was more potent against MDR1-overexpressing MCF7/adr breast cancer xenografts with a relative tumor growth rate of 12.3% than paclitaxel with a rate of 43.0%. BFBTS displays a novel antimicrotubule agent with potentials for cancer therapeutics. [Mol Cancer Ther 2009;8(12):3318–30]

17 November 2023
Verified
Conference Paper
Closed access
JLJianqiao Luo
Jianqiao Luo
YMYang Mo
Yang Mo
YWYaonan Wang
Yaonan Wang
XXXu Xiao
Xu Xiao
Sichuan peppers are delicious spices and its autonomous robotic harvesting requires the estimation of pepper pose on the farm. The pepper pose estimation task can be casted as ordinal classification problems by defining a number of pose labels. Since adjacent pose labels share resembling appearance, there exists label ambiguity in many pepper images and ambiguity degree of different images is changing. Label distribution learning (LDL) can handle label ambiguity by converting a single label to a label distribution. Recent LDL methods measure ambiguity degree through training losses, which mainly indicate epistemic uncertainty (EU) and consequently prone to underestimate the ambiguity variations among different samples. To address this issue, we propose a novel LDL method for pepper pose estimation, by measuring ambiguity degrees through aleatoric uncertainty (AU) rather than EU. In specific, we fist leverage Bayesian neural network to quantify sample AU values, which express the inherent noise in observations and thus can sufficiently capture the variations in pose ambiguity. Then, AU values are used to adjust the variance of label distributions so that samples with higher AU values are associated with more flattened distributions. Finally, the instance-aware label distributions are leveraged to train networks for pepper pose estimation. Experimental results on pepper images collected on the farm show that, our method achieve the overall accuracy of 81.28%, outperforming recent leading LDL methods in performance.