Search Results for author: Xiaoyang Wang

Found 39 papers, 11 papers with code

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning

no code implementations30 Sep 2023 Xuansheng Wu, Wenlin Yao, Jianshu Chen, Xiaoman Pan, Xiaoyang Wang, Ninghao Liu, Dong Yu

Large Language Models (LLMs) have achieved remarkable success, demonstrating powerful instruction-following capabilities across diverse tasks.

Unsupervised Multi-document Summarization with Holistic Inference

no code implementations8 Sep 2023 Haopeng Zhang, Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Hongwei Wang, Jiawei Zhang, Dong Yu

SRI balances the importance and diversity of a subset of sentences from the source documents and can be calculated in unsupervised and adaptive manners.

Document Summarization Extractive Summarization +1

Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models

no code implementations1 Aug 2023 Jiaao Chen, Xiaoman Pan, Dian Yu, Kaiqiang Song, Xiaoyang Wang, Dong Yu, Jianshu Chen

Compositional generalization empowers the LLMs to solve problems that are harder than the ones they have seen (i. e., easy-to-hard generalization), which is a critical reasoning capability of human-like intelligence.

Mathematical Reasoning Math Word Problem Solving

FedMLSecurity: A Benchmark for Attacks and Defenses in Federated Learning and LLMs

1 code implementation8 Jun 2023 Shanshan Han, Baturalp Buyukates, Zijian Hu, Han Jin, Weizhao Jin, Lichao Sun, Xiaoyang Wang, Wenxuan Wu, Chulin Xie, Yuhang Yao, Kai Zhang, Qifan Zhang, Yuhui Zhang, Salman Avestimehr, Chaoyang He

This paper introduces FedMLSecurity, a benchmark designed to simulate adversarial attacks and corresponding defense mechanisms in Federated Learning (FL).

Federated Learning

Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction

no code implementations2 Jun 2023 Canjia Li, Xiaoyang Wang, Dongdong Li, Yiding Liu, Yu Lu, Shuaiqiang Wang, Zhicong Cheng, Simiu Gu, Dawei Yin

In this work, we focus on ranking user satisfaction rather than relevance in web search, and propose a PLM-based framework, namely SAT-Ranker, which comprehensively models different dimensions of user satisfaction in a unified manner.

Language Modelling

Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks

no code implementations24 Feb 2023 Mohammud J. Bocus, Xiaoyang Wang, Robert. J. Piechocki

This paper presents a novel approach for multimodal data fusion based on the Vector-Quantized Variational Autoencoder (VQVAE) architecture.

FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction

no code implementations ICCV 2023 Zheng Fang, Xiaoyang Wang, Haocheng Li, Jiejie Liu, Qiugui Hu, Jimin Xiao

In this paper, we propose a few-shot anomaly detection strategy that works in a low-data regime and can generalize across products at no cost.

Anomaly Detection

Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation

1 code implementation CVPR 2023 Xiaoyang Wang, Bingfeng Zhang, Limin Yu, Jimin Xiao

Inspired by density-based unsupervised clustering, we propose to leverage feature density to locate sparse regions within feature clusters defined by label and pseudo labels.

Contrastive Learning Density Estimation +1

OASum: Large-Scale Open Domain Aspect-based Summarization

1 code implementation19 Dec 2022 Xianjun Yang, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Xiaoman Pan, Linda Petzold, Dong Yu

Specifically, zero/few-shot and fine-tuning results show that the model pre-trained on our corpus demonstrates a strong aspect or query-focused generation ability compared with the backbone model.

Salience Allocation as Guidance for Abstractive Summarization

1 code implementation22 Oct 2022 Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu

Recent literature adds extractive summaries as guidance for abstractive summarization models to provide hints of salient content and achieves better performance.

Abstractive Text Summarization

Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination

1 code implementation21 Oct 2022 Yue Yang, Wenlin Yao, Hongming Zhang, Xiaoyang Wang, Dong Yu, Jianshu Chen

Large-scale pretrained language models have made significant advances in solving downstream language understanding tasks.

Language Modelling Retrieval +1

Invariant Aggregator for Defending against Federated Backdoor Attacks

no code implementations4 Oct 2022 Xiaoyang Wang, Dimitrios Dimitriadis, Sanmi Koyejo, Shruti Tople

Empirical results on three datasets with different modalities and varying numbers of clients further demonstrate that our approach mitigates a broad class of backdoor attacks with a negligible cost on the model utility.

Federated Learning Model Optimization

Federated Meta-Learning for Traffic Steering in O-RAN

no code implementations13 Sep 2022 Hakan Erdol, Xiaoyang Wang, Peizheng Li, Jonathan D. Thomas, Robert Piechocki, George Oikonomou, Rui Inacio, Abdelrahim Ahmad, Keith Briggs, Shipra Kapoor

In order to provide such services, 5G systems will support various combinations of access technologies such as LTE, NR, NR-U and Wi-Fi.

Management Meta-Learning

Multimodal sensor fusion in the latent representation space

no code implementations3 Aug 2022 Robert J. Piechocki, Xiaoyang Wang, Mohammud J. Bocus

In the second stage, the generative model serves as a reconstruction prior and the search manifold for the sensor fusion tasks.

Denoising Sensor Fusion

Sim2real for Reinforcement Learning Driven Next Generation Networks

no code implementations8 Jun 2022 Peizheng Li, Jonathan Thomas, Xiaoyang Wang, Hakan Erdol, Abdelrahim Ahmad, Rui Inacio, Shipra Kapoor, Arjun Parekh, Angela Doufexi, Arman Shojaeifard, Robert Piechocki

One of the main reasons is the modelling gap between the simulation and the real environment, which could make the RL agent trained by simulation ill-equipped for the real environment.

reinforcement-learning Reinforcement Learning (RL)

RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN

no code implementations12 Nov 2021 Peizheng Li, Jonathan Thomas, Xiaoyang Wang, Ahmed Khalil, Abdelrahim Ahmad, Rui Inacio, Shipra Kapoor, Arjun Parekh, Angela Doufexi, Arman Shojaeifard, Robert Piechocki

We provide a taxonomy for the challenges faced by ML/RL models throughout the development life-cycle: from the system specification to production deployment (data acquisition, model design, testing and management, etc.).

Management reinforcement-learning +1

Robust and Personalized Federated Learning with Spurious Features: an Adversarial Approach

no code implementations29 Sep 2021 Xiaoyang Wang, Han Zhao, Klara Nahrstedt, Oluwasanmi O Koyejo

To this end, we propose a strategy to mitigate the effect of spurious features based on our observation that the global model in the federated learning step has a low accuracy disparity due to statistical heterogeneity.

Personalized Federated Learning

AppQ: Warm-starting App Recommendation Based on View Graphs

no code implementations8 Sep 2021 Dan Su, Jiqiang Liu, Sencun Zhu, Xiaoyang Wang, Wei Wang, Xiangliang Zhang

In this work, we propose AppQ, a novel app quality grading and recommendation system that extracts inborn features of apps based on app source code.

Recommendation Systems

Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection

1 code implementation24 Jul 2021 Zhenguang Liu, Peng Qian, Xiaoyang Wang, Yuan Zhuang, Lin Qiu, Xun Wang

Then, we propose a novel temporal message propagation network to extract the graph feature from the normalized graph, and combine the graph feature with designed expert patterns to yield a final detection system.

Vulnerability Detection

Self-play Learning Strategies for Resource Assignment in Open-RAN Networks

no code implementations3 Mar 2021 Xiaoyang Wang, Jonathan D Thomas, Robert J Piechocki, Shipra Kapoor, Raul Santos-Rodriguez, Arjun Parekh

Open Radio Access Network (ORAN) is being developed with an aim to democratise access and lower the cost of future mobile data networks, supporting network services with various QoS requirements, such as massive IoT and URLLC.

Edge-computing Management

NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation

no code implementations3 Mar 2021 Xiaoyang Wang, Chen Li, Jianqiao Zhao, Dong Yu

To facilitate the research on this corpus, we provide results of several benchmark models.

Robusta: Robust AutoML for Feature Selection via Reinforcement Learning

no code implementations15 Jan 2021 Xiaoyang Wang, Bo Li, Yibo Zhang, Bhavya Kailkhura, Klara Nahrstedt

However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks.

AutoML Feature Importance +3

Identifying Coarse-grained Independent Causal Mechanisms with Self-supervision

1 code implementation 1st Conference on Causal Learning and Reasoning 2022 Xiaoyang Wang, Klara Nahrstedt, Oluwasanmi O Koyejo

Current approaches for learning disentangled representations assume that independent latent variables generate the data through a single data generation process.

Automatic Summarization of Open-Domain Podcast Episodes

no code implementations9 Nov 2020 Kaiqiang Song, Chen Li, Xiaoyang Wang, Dong Yu, Fei Liu

Instead, we investigate several less-studied aspects of neural abstractive summarization, including (i) the importance of selecting important segments from transcripts to serve as input to the summarizer; (ii) striking a balance between the amount and quality of training instances; (iii) the appropriate summary length and start/end points.

Abstractive Text Summarization

Graph Neural Network for Fraud Detection via Spatial-Temporal Attention

1 code implementation TKDE 2020 Dawei Cheng, Xiaoyang Wang, Ying Zhang, Liqing Zhang

But manually generating features needs domain knowledge and may lay behind the modus operandi of fraud, which means we need to automatically focus on the most relevant fraudulent behavior patterns in the online detection system.

Fraud Detection

Lipschitz Learning for Signal Recovery

no code implementations4 Oct 2019 Hong Jiang, Jong-Hoon Ahn, Xiaoyang Wang

We will develop a theoretical framework to characterize the signals that can be robustly recovered from their observations by an ML algorithm, and establish a Lipschitz condition on signals and observations that is both necessary and sufficient for the existence of a robust recovery.

Compressive Sensing

STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification

no code implementations9 Nov 2018 Yang Fu, Xiaoyang Wang, Yunchao Wei, Thomas Huang

Thus, a more robust clip-level feature representation can be generated according to a weighted sum operation guided by the mined 2-D attention score matrix.

Large-Scale Person Re-Identification Video-Based Person Re-Identification

Request-and-Reverify: Hierarchical Hypothesis Testing for Concept Drift Detection with Expensive Labels

no code implementations25 Jun 2018 Shujian Yu, Xiaoyang Wang, Jose C. Principe

In this paper, a novel Hierarchical Hypothesis Testing framework with Request-and-Reverify strategy is developed to detect concept drifts by requesting labels only when necessary.

General Classification Two-sample testing

Video Event Recognition With Deep Hierarchical Context Model

no code implementations CVPR 2015 Xiaoyang Wang, Qiang Ji

Video event recognition still faces great challenges due to large intra-class variation and low image resolution, in particular for surveillance videos.

Cannot find the paper you are looking for? You can Submit a new open access paper.