Search Results for author: Xiangyu Wang

Found 39 papers, 7 papers with code

UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning

no code implementations21 May 2025 Xiangyu Wang, Donglin Yang, Yue Liao, Wenhao Zheng, Wenjun Wu, Bin Dai, Hongsheng Li, Si Liu

Unmanned Aerial Vehicles (UAVs) are evolving into language-interactive platforms, enabling more intuitive forms of human-drone interaction.

Benchmarking Imitation Learning

Reservoir-enhanced Segment Anything Model for Subsurface Diagnosis

1 code implementation26 Apr 2025 Xiren Zhou, Shikang Liu, Xinyu Yan, Yizhan Fan, Xiangyu Wang, Yu Kang, Jian Cheng, Huanhuan Chen

Urban roads and infrastructure, vital to city operations, face growing threats from subsurface anomalies like cracks and cavities.

Anomaly Detection GPR +1

Generative Evaluation of Complex Reasoning in Large Language Models

1 code implementation3 Apr 2025 Haowei Lin, Xiangyu Wang, Ruilin Yan, Baizhou Huang, Haotian Ye, Jianhua Zhu, ZiHao Wang, James Zou, Jianzhu Ma, Yitao Liang

Moreover, LLM performance on KUMO tasks correlates strongly with results on newly released real-world reasoning benchmarks, underscoring KUMO's value as a robust, enduring assessment tool for genuine LLM reasoning capabilities.

Benchmarking Memorization

A Sustainable Circular Framework for Financing Infrastructure Climate Adaptation: Integrated Carbon Markets

no code implementations14 Jan 2025 Chao Li, Xing Su, Chao Fan, Jun Wang, Xiangyu Wang

Climate physical risks pose an increasing threat to urban infrastructure, necessitating urgent climate adaptation measures to protect lives and assets.

MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM

no code implementations5 Dec 2024 Changcheng Li, Xiangyu Wang, Qiuju Chen, Xiren Zhou, Huanhuan Chen

Large language models (LLMs) have shown limitations in tasks requiring complex logical reasoning and multi-step problem-solving.

counterfactual Form +1

Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology

no code implementations9 Oct 2024 Xiangyu Wang, Donglin Yang, Ziqin Wang, Hohin Kwan, Jinyu Chen, Wenjun Wu, Hongsheng Li, Yue Liao, Si Liu

Developing agents capable of navigating to a target location based on language instructions and visual information, known as vision-language navigation (VLN), has attracted widespread interest.

Vision-Language Navigation

Real-time Detection and Auto focusing of Beam Profiles from Silicon Photonics Gratings using YOLO model

no code implementations22 Sep 2024 Yu Dian Lim, Hong Yu Li, Simon Chun Kiat Goh, Xiangyu Wang, Peng Zhao, Chuan Seng Tan

When observing the chip-to-free-space light beams from silicon photonics (SiPh) to free-space, manual adjustment of camera lens is often required to obtain a focused image of the light beams.

Towards Weather-Robust 3D Human Body Reconstruction: Millimeter-Wave Radar-Based Dataset, Benchmark, and Multi-Modal Fusion

no code implementations7 Sep 2024 Anjun Chen, Xiangyu Wang, Kun Shi, Yuchi Huo, Jiming Chen, Qi Ye

With this dataset, we conduct a comprehensive analysis about the limitations of single-modality reconstruction and the impact of missing points and sparsity on the reconstruction performance.

3D Human Reconstruction

Recognizing Beam Profiles from Silicon Photonics Gratings using Transformer Model

no code implementations19 Aug 2024 Yu Dian Lim, Hong Yu Li, Simon Chun Kiat Goh, Xiangyu Wang, Peng Zhao, Chuan Seng Tan

In this work, we developed transformer models to recognize the corresponding height categories of beam profiles of light from SiPh gratings.

A Unified Framework for Combinatorial Optimization Based on Graph Neural Networks

no code implementations19 Jun 2024 Yaochu Jin, Xueming Yan, Shiqing Liu, Xiangyu Wang

Graph neural networks (GNNs) have emerged as a powerful tool for solving combinatorial optimization problems (COPs), exhibiting state-of-the-art performance in both graph-structured and non-graph-structured domains.

Combinatorial Optimization

Async Learned User Embeddings for Ads Delivery Optimization

no code implementations9 Jun 2024 Mingwei Tang, Meng Liu, Hong Li, Junjie Yang, Chenglin Wei, Boyang Li, Dai Li, Rengan Xu, Yifan Xu, Zehua Zhang, Xiangyu Wang, Linfeng Liu, Yuelei Xie, Chengye Liu, Labib Fawaz, Li Li, Hongnan Wang, Bill Zhu, Sri Reddy

In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance.

Graph Learning Recommendation Systems +1

Confidence-aware Contrastive Learning for Selective Classification

1 code implementation7 Jun 2024 Yu-Chang Wu, Shen-Huan Lyu, Haopu Shang, Xiangyu Wang, Chao Qian

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios.

Classification Contrastive Learning

Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields

1 code implementation ICCV 2023 Xiangyu Wang, Jingsen Zhu, Qi Ye, Yuchi Huo, Yunlong Ran, Zhihua Zhong, Jiming Chen

With the popularity of implicit neural representations, or neural radiance fields (NeRF), there is a pressing need for editing methods to interact with the implicit 3D models for tasks like post-processing reconstructed scenes and 3D content creation.

NeRF

From Query Tools to Causal Architects: Harnessing Large Language Models for Advanced Causal Discovery from Data

no code implementations29 Jun 2023 Taiyu Ban, Lyvzhou Chen, Xiangyu Wang, Huanhuan Chen

In this paper, we advance the current research of LLM-driven causal discovery by proposing a novel framework that combines knowledge-based LLM causal analysis with data-driven causal structure learning.

Causal Discovery

Mitigating Prior Errors in Causal Structure Learning: Towards LLM driven Prior Knowledge

no code implementations12 Jun 2023 Lyuzhou Chen, Taiyu Ban, Xiangyu Wang, Derui Lyu, Huanhuan Chen

LLM presents strong capability in discovering causal relationships between variables with the "text" inputs defining the investigated variables, leading to a potential new hierarchy and new ladder of causality.

GIMM: InfoMin-Max for Automated Graph Contrastive Learning

no code implementations27 May 2023 Xin Xiong, Furao Shen, Xiangyu Wang, Jian Zhao

Many GCL methods with automated data augmentation face the risk of insufficient information as they fail to preserve the essential information necessary for the downstream task.

Contrastive Learning Data Augmentation +2

Long-Term Value of Exploration: Measurements, Findings and Algorithms

no code implementations12 May 2023 Yi Su, Xiangyu Wang, Elaine Ya Le, Liang Liu, Yuening Li, Haokai Lu, Benjamin Lipshitz, Sriraj Badam, Lukasz Heldt, Shuchao Bi, Ed Chi, Cristos Goodrow, Su-Lin Wu, Lexi Baugher, Minmin Chen

We conduct live experiments on one of the largest short-form video recommendation platforms that serves billions of users to validate the new experiment designs, quantify the long-term values of exploration, and to verify the effectiveness of the adopted neural linear bandit algorithm for exploration.

Recommendation Systems

A Graph Neural Network with Negative Message Passing for Graph Coloring

no code implementations26 Jan 2023 Xiangyu Wang, Xueming Yan, Yaochu Jin

In this paper, we propose a graph network model for graph coloring, which is a class of representative heterophilous problems.

Graph Neural Network

ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions

no code implementations4 Oct 2022 Anjun Chen, Xiangyu Wang, Kun Shi, Shaohao Zhu, Bin Fang, Yingfeng Chen, Jiming Chen, Yuchi Huo, Qi Ye

However, combining RGB and mmWave signals for robust all-weather 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images.

3D Human Reconstruction All

mmBody Benchmark: 3D Body Reconstruction Dataset and Analysis for Millimeter Wave Radar

no code implementations12 Sep 2022 Anjun Chen, Xiangyu Wang, Shaohao Zhu, Yanxu Li, Jiming Chen, Qi Ye

The results demonstrate that 1) despite the noise and sparsity of the generated point clouds, the mmWave radar can achieve better reconstruction accuracy than the RGB camera but worse than the depth camera; 2) the reconstruction from the mmWave radar is affected by adverse weather conditions moderately while the RGB(D) camera is severely affected.

Distributed Representations of Emotion Categories in Emotion Space

no code implementations ACL 2021 Xiangyu Wang, Chengqing Zong

Emotion category is usually divided into different ones by human beings, but it is indeed difficult to clearly distinguish and define the boundaries between different emotion categories.

Emotion Classification

SE-Harris and eSUSAN: Asynchronous Event-Based Corner Detection Using Megapixel Resolution CeleX-V Camera

no code implementations2 May 2021 Jinjian Li, Chuandong Guo, Li Su, Xiangyu Wang, Quan Hu

The proposed eSUSAN extracts the univalue segment assimilating nucleus from the circle kernel based on the similarity across timestamps and distinguishes corner events by the number of pixels in the nucleus area.

Boosting Variational Inference

no code implementations17 Nov 2016 Fangjian Guo, Xiangyu Wang, Kai Fan, Tamara Broderick, David B. Dunson

Variational inference (VI) provides fast approximations of a Bayesian posterior in part because it formulates posterior approximation as an optimization problem: to find the closest distribution to the exact posterior over some family of distributions.

Variational Inference

Unsupervised Cross-Media Hashing with Structure Preservation

no code implementations18 Mar 2016 Xiangyu Wang, Alex Yong-Sang Chia

Here, given a query of any media type, cross-media retrieval seeks to find relevant results of different media types from heterogeneous data sources.

Retrieval

Towards Unifying Hamiltonian Monte Carlo and Slice Sampling

no code implementations NeurIPS 2016 Yizhe Zhang, Xiangyu Wang, Changyou Chen, Ricardo Henao, Kai Fan, Lawrence Carin

We unify slice sampling and Hamiltonian Monte Carlo (HMC) sampling, demonstrating their connection via the Hamiltonian-Jacobi equation from Hamiltonian mechanics.

A Direct Approach for Sparse Quadratic Discriminant Analysis

no code implementations1 Oct 2015 Binyan Jiang, Xiangyu Wang, Chenlei Leng

Formulated in a simple and coherent framework, DA-QDA aims to directly estimate the key quantities in the Bayes discriminant function including quadratic interactions and a linear index of the variables for classification.

General Classification

Parallelizing MCMC with Random Partition Trees

2 code implementations NeurIPS 2015 Xiangyu Wang, Fangjian Guo, Katherine A. Heller, David B. Dunson

The new algorithm applies random partition trees to combine the subset posterior draws, which is distribution-free, easy to resample from and can adapt to multiple scales.

Bayesian Inference

No penalty no tears: Least squares in high-dimensional linear models

no code implementations7 Jun 2015 Xiangyu Wang, David Dunson, Chenlei Leng

Ordinary least squares (OLS) is the default method for fitting linear models, but is not applicable for problems with dimensionality larger than the sample size.

regression Vocal Bursts Intensity Prediction

High-dimensional Ordinary Least-squares Projection for Screening Variables

no code implementations5 Jun 2015 Xiangyu Wang, Chenlei Leng

Variable selection is a challenging issue in statistical applications when the number of predictors $p$ far exceeds the number of observations $n$.

Variable Selection Vocal Bursts Intensity Prediction

Protecting Against Screenshots: An Image Processing Approach

no code implementations CVPR 2015 Alex Yong-Sang Chia, Udana Bandara, Xiangyu Wang, Hiromi Hirano

We model this blending of information by an additive process, and exploit this to design a visual contents distortion algorithm that supports real-time contents recovery by the human visual system.

Median Selection Subset Aggregation for Parallel Inference

no code implementations NeurIPS 2014 Xiangyu Wang, Peichao Peng, David Dunson

For massive data sets, efficient computation commonly relies on distributed algorithms that store and process subsets of the data on different machines, minimizing communication costs.

feature selection Model Selection +1

Parallelizing MCMC via Weierstrass Sampler

1 code implementation17 Dec 2013 Xiangyu Wang, David B. Dunson

With the rapidly growing scales of statistical problems, subset based communication-free parallel MCMC methods are a promising future for large scale Bayesian analysis.

Computational Efficiency

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