Author name cluster

Kehan Chen

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

1 author row

AAAI Conference 2025 Conference Paper

Learning Fine-Grained Alignment for Aerial Vision-Dialog Navigation

Yifei Su
Dong An
Kehan Chen
Weichen Yu
Baiyang Ning
Yonggen Ling
Yan Huang
Liang Wang

Aerial Vision-Dialog Navigation (AVDN) is a new task that requires drones to navigate to a target location based on human-robot dialog history. This paper focuses on the critical fine-grained cross-modal alignment problem in AVDN, requiring the drone to align language entities with visual landmarks in top-down views. To achieve this, we first construct a Fine-Grained AVDN (FG-AVDN) dataset via a semi-automatic annotation pipeline, providing diverse multimodal annotations at the entity-landmark level. Based on this, a novel Fine-grained Entity-Landmark Alignment (FELA) method is proposed to learn the cross-modal alignment explicitly. Concretely, FELA first boosts the drone's visual understanding with a precise semantic grid representation, which captures the environmental semantics and spatial structure simultaneously. Subsequently, to learn the entity-landmark alignment, we devise cross-modal auxiliary tasks from three perspectives, including grounding, captioning, and contrastive learning. Extensive experiments demonstrate that our explicit entity-landmark alignment learning is beneficial for AVDN. As a result, FELA achieves leading performance with 3.2% SR and 4.9% GP improvements over prior arts. Code and dataset will be publicly available.

PDF Details DOI

EAAI Journal 2025 Journal Article

Lightning risk assessment of offshore wind farms considering tropical cyclone impacts based on an improved gradient boosting algorithm

Qibin Zhou
Kehan Chen
Xiaoyan Bian
Shangjie Chen
Gaopeng Lu

In recent years, global climate warming has led to a significant increase in both the frequency and intensity of tropical cyclones (TCs). The development of TCs is often accompanied by frequent lightning activities. The risk of lightning strikes to high offshore wind turbines is substantially elevated. This study evaluates the lightning risk faced by offshore wind farms influenced by tropical cyclones. Firstly, TC paths are analyzed in both spatial and temporal dimensions by linking them with lightning data to examine the distribution of TC-related lightning, and the lightning strike characteristics of offshore wind turbines are investigated. Secondly, a Bayesian Optimization (BO)-based eXtreme Gradient Boosting (XGBoost) model for lightning risk assessment is proposed, incorporating characteristics of TC lightning and offshore wind farms as input variables. The proposed BO-XGBoost model outperforms XGBoost, Bidirectional Long Short-Term Memory (Bi-LSTM), Support Vector Machine (SVM) and Neural Network (NN), achieving a precision of 98. 9 % and a recall of 98. 9 % on the test set. Additionally, SHapley Additive exPlanations (SHAP) value analysis indicates that TC lightning characteristics and offshore wind farm characteristics significantly impact the model output, enhancing the accuracy of the model. The assessment outcomes provide a theoretical basis for future offshore wind farm planning and guidance for lightning protection measures in offshore wind farms.

Details DOI

NeurIPS Conference 2024 Conference Paper

Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor

Keji He
Kehan Chen
Jiawang Bai
Yan Huang
Qi Wu
Shu-Tao Xia
Liang Wang

Vision-and-Language Navigation (VLN) requires an agent to dynamically explore environments following natural language. The VLN agent, closely integrated into daily lives, poses a substantial threat to the security of privacy and property upon the occurrence of malicious behavior. However, this serious issue has long been overlooked. In this paper, we pioneer the exploration of an object-aware backdoored VLN, achieved by implanting object-aware backdoors during the training phase. Tailored to the unique VLN nature of cross-modality and continuous decision-making, we propose a novel backdoored VLN paradigm: IPR Backdoor. This enables the agent to act in abnormal behavior once encountering the object triggers during language-guided navigation in unseen environments, thereby executing an attack on the target scene. Experiments demonstrate the effectiveness of our method in both physical and digital spaces across different VLN agents, as well as its robustness to various visual and textual variations. Additionally, our method also well ensures navigation performance in normal scenarios with remarkable stealthiness.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Code-Aware Cross-Program Transfer Hyperparameter Optimization

Zijia Wang
Xiangyu He
Kehan Chen
Chen Lin
Jinsong Su

Hyperparameter tuning is an essential task in automatic machine learning and big data management. To accelerate tuning, many recent studies focus on augmenting BO, the primary hyperparameter tuning strategy, by transferring information from other tuning tasks. However, existing studies ignore program similarities in their transfer mechanism, thus they are sub-optimal in cross-program transfer when tuning tasks involve different programs. This paper proposes CaTHPO, a code-aware cross-program transfer hyperparameter optimization framework, which makes three improvements. (1) It learns code-aware program representation in a self-supervised manner to give an off-the-shelf estimate of program similarities. (2) It adjusts the surrogate and AF in BO based on program similarities, thus the hyperparameter search is guided by accumulated information across similar programs. (3) It presents a safe controller to dynamically prune undesirable sample points based on tuning experiences of similar programs. Extensive experiments on tuning various recommendation models and Spark applications have demonstrated that CatHPO can steadily obtain better and more robust hyperparameter performances within fewer samples than state-of-the-art competitors.

PDF Details DOI