Author name cluster

Feilong Wang

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.

4 papers

2 author rows

ICRA Conference 2025 Conference Paper

Knowledge-Driven Visual Target Navigation: Dual Graph Navigation

Shiyao Li
Ziyang Meng
Jiansong Pei
Jiahao Chen
Bingcheng Dong
Guangsheng Li
Shenglan Liu 0001
Feilong Wang

In unknown environments, navigating a robot by a given image to a specific location or instance is critical and challenging. The existing end-to-end approaches require simultaneous implicit learning of multiple subtasks, and modular approaches depend on metric information. Both approaches face high computational demands, often leading to difficulties in real-time updates and limited generalization, making them challenging to implement on resource-constrained devices. To address these challenges, we propose Dual Graph Navigation (DGN), a knowledge-driven, lightweight image instance navigation framework. DGN builds an External Knowledge Graph (EKG) from small-scale datasets to capture prior object correlations, efficiently guiding target exploration. During exploration, DGN builds an Internal Knowledge Graph (IKG) using an instance-aware module, which records explored objects based on reachability relationships rather than precise metric information. The IKG dynamically updates the EKG, enhancing the robot's adaptability to the current environment. Together, they realize topological perception and reduce computational overhead. Furthermore, unlike approaches characterized by over-dependence between components, DGN employs a plug-and-play modular design that allows independent training and flexible replacement of functional modules, effectively enhancing generalization performance while reducing training and deployment costs. Experiments illustrate that DGN generalizes well in different simulation environments (AI2-THOR, Habitat), achieving state-of-the-art performance on the ProcTHOR-10K dataset. It is compatible with three distinct real-world robot platforms, including edge computing devices without CUDA support. It exhibits a decision-making speed of 3. 8 to 5. 5 times over baseline methods. Further details can be found on the project page: https://dogplanningloyo.github.io/DGN/.

Details

EAAI Journal 2025 Journal Article

Leveraging large language models to examine the interaction between investor sentiment and stock performance

Yong Zhuang
Feilong Wang
Dickson K.W. Chiu
Kevin K.W. Ho

Understanding the relationship between investor sentiment and stock performance is crucial in dynamic financial markets. Existing researches often focus on financial news and stock prices, while studies on investor sentiment typically rely on traditional machine learning models that require extensive data labeling. Additionally, most researches focus on single stock indices, overlooking the impact of brand popularity. To address these gaps, this study proposes a novel framework to analyze the interaction between investor sentiment and stock performance, using Chinese Baijiu industry stocks as a case example. It further explores how brand popularity influences this relationship, offering insights for informed investment decisions through artificial intelligence technology. In this study, we leverage Generative Pre-trained Transformer 4 (GPT-4), a state-of-the-art black-box large language model, to process vast volumes of unstructured text data from stock forums. By employing in-context learning with human-labeled examples, GPT-4 generates weak labels that are subsequently used to fine-tune Large Language Model Meta AI (LLaMA), a smaller and more efficient open-source LLM from Meta AI, thereby enabling sentiment-driven decision-making in real-world scenarios. To construct a comprehensive sentiment indicator, we integrate both direct and indirect factors influencing sentiment and use principal component analysis to combine them effectively. To examine interaction between sentiment and stock yield, we apply the Granger causality test and vector autoregression models across stocks with different brand popularity levels. The results show that our framework achieves state-of-the-art performance investor sentiment analysis. Moreover, with brand popularity significantly amplifying the interaction between investor sentiment and stock yield, it leads to bidirectional Granger causality in highly popular brands.

Details DOI

AAAI Conference 2025 Conference Paper

Set-Valued Sensitivity Analysis of Deep Neural Networks

Xin Wang
Feilong Wang
Xuegang (Jeff) Ban

This paper proposes a sensitivity analysis framework based on set-valued mapping for deep neural networks (DNN) to understand and compute how the solutions (model weights) of DNN respond to perturbations in the training data. As a DNN may not exhibit a unique solution (minima) and the algorithm of solving a DNN may lead to different solutions with minor perturbations to input data, we focus on the sensitivity of the solution set of DNN, instead of studying a single solution. In particular, we are interested in the expansion and contraction of the solution set in response to data perturbations. If the change of solution set can be bounded by the extent of the data perturbation, the model is said to exhibit the Lipschitz-like property. This 'set-to-set' analysis approach provides a deeper understanding of the robustness and reliability of DNNs during training. Our framework incorporates both isolated and non-isolated minima, and critically, does not require the assumption that the Hessian of loss function is non-singular. By developing set-level metrics such as distance between sets, convergence of sets, derivatives of set-valued mapping, and stability across the solution set, we prove that the solution set of the Fully Connected Neural Network holds Lipschitz-like properties. For general neural networks (e.g. Resnet), we introduce a graphical-derivative-based method to estimate the new solution set following data perturbation without retraining.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Vision Shared and Representation Isolated Network for Person Search

Yang Liu
Yingping Li
Chengyu Kong
Yuqiu Kong
Shenglan Liu
Feilong Wang

Person search is a widely-concerned computer vision task that aims to jointly solve the problems of pedestrian detection and person re-identification in panoramic scenes. However, the pedestrian detection focuses on the consistency of pedestrians, while the person re-identification attempts to extract the discriminative features of pedestrians. The inevitable conflict greatly restricts the researches on the one-stage person search methods. To address this issue, we propose a Vision Shared and Representation Isolated (VSRI) network to decouple the two conflicted subtasks simultaneously, through which two independent representations are constructed for the two subtasks. To enhance the discrimination of the re-ID representation, a Multi-Level Feature Fusion (MLFF) module is proposed. The MLFF adopts the Spatial Pyramid Feature Fusion (SPFF) module to obtain diverse features from the stem network. Moreover, the multi-head self-attention mechanism is employed to construct a Multi-head Attention Driven Extraction (MADE) module and the cascaded convolution unit is adopted to devise a Feature Decomposition and Cascaded Integration (FDCI) module, which facilitates the MLFF to obtain more discriminative representations of the pedestrians. The proposed method outperforms the state-of-the-art methods on the mainstream datasets.

PDF Details DOI