arXiv subjects

Zicheng Su

Publications and source records attributed to Zicheng Su.

5 recordsLinked to original sources

arXiv2026

PriEco-DRL: Joint Optimization of Electric-Bus Eco-Driving and Transit-Priority Adaptive Signals via Deep Reinforcement Learning

Urban transit electrification requires balancing energy efficiency, schedule reliability, and ride comfort for electric buses (EBs), particularly when interacting with transit-priority adaptive signals in congested networks. This paper proposes PriEco-DRL, a joint optimization framework that integrates EB eco-driving with transit-priority adaptive signal control using deep reinforcement learning (DRL). The signal layer employs a priority-weighted max-pressure (Priority-MP) controller to allocate green time based on occupancy-aware pressures, while the vehicle layer adapts longitudinal control based on uncertain and dynamically evolving local signal cues. A structured reward combines guidance and event-based reinforcement to align EB arrivals with green opportunities while considering energy, time, comfort, and safety. The framework uses centralized training and decentralized execution (CTDE) with parameter sharing, allowing a single DRL agent to learn from multiple buses and routes using local observations. Experiments on a real-world corridor show that PriEco-DRL reduces EB energy consumption while maintaining network efficiency and transit priority compared with fixed-time, actuated, and rule-based signal-vehicle coordination baselines. Energy- and trajectory-based analyses reveal that the improvements stem from fewer unscheduled stop-start events and smoother speed regulation under adaptive signals. The results highlight a tunable energy-time trade-off, allowing flexible operational choices through reward weighting.

math.OC↗

arXiv2026

RTCFake: Speech Deepfake Detection in Real-Time Communication

With the rapid advancement of speech generation technologies, the threat posed by speech deepfakes in real-time communication (RTC) scenarios has intensified. However, existing detection studies mainly focus on offline simulations and struggle to cope with the complex distortions introduced during RTC transmission, including unknown speech enhancement processes (e.g., noise suppression) and codec compression. To address this challenge, we present the first large-scale speech deepfake dataset tailored for RTC scenarios, termed \textit{RTCFake}, totaling approximately 600 hours. The dataset is constructed by transmitting speech through multiple mainstream social media and conferencing platforms (e.g., Zoom), enabling precise pairing between offline and online speech. In addition, we propose a phoneme-guided consistency learning (PCL) strategy that enforces models to learn platform-invariant semantic structural representations. In this paper, the RTCFake dataset is divided into training, development, and evaluation sets. The evaluation set further includes both unseen RTC platforms and unseen complex noise conditions, thereby providing a more realistic and challenging evaluation benchmark for speech deepfake detection. Furthermore, the proposed PCL strategy achieves significant improvements in both cross-platform generalization and noise robustness, offering an effective and generalizable modeling paradigm. The \textit{RTCFake} dataset is provided in the {https://huggingface.co/datasets/JunXueTech/RTCFake}.

cs.SD↗

arXiv2025

TraSculptor: Visual Analytics for Enhanced Decision-Making in Road Traffic Planning

The design of urban road networks significantly influences traffic conditions, underscoring the importance of informed traffic planning. Traffic planning experts rely on specialized platforms to simulate traffic systems, assessing the efficacy of the road network across various states of modifications. Nevertheless, a prevailing issue persists: many existing traffic planning platforms exhibit inefficiencies in flexibly interacting with the road network's structure and attributes and intuitively comparing multiple states during the iterative planning process. This paper introduces TraSculptor, an interactive planning decision-making system. To develop TraSculptor, we identify and address two challenges: interactive modification of road networks and intuitive comparison of multiple network states. For the first challenge, we establish flexible interactions to enable experts to easily and directly modify the road network on the map. For the second challenge, we design a comparison view with a history tree of multiple states and a road-state matrix to facilitate intuitive comparison of road network states. To evaluate TraSculptor, we provided a usage scenario where the Braess's paradox was showcased, invited experts to perform a case study on the Sioux Falls network, and collected expert feedback through interviews.

cs.HC↗

arXiv2025

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models

Unmanned Aerial Vehicle (UAV) Vision-and-Language Navigation (VLN) is vital for applications such as disaster response, logistics delivery, and urban inspection. However, existing methods often struggle with insufficient multimodal fusion, weak generalization, and poor interpretability. To address these challenges, we propose FlightGPT, a novel UAV VLN framework built upon Vision-Language Models (VLMs) with powerful multimodal perception capabilities. We design a two-stage training pipeline: first, Supervised Fine-Tuning (SFT) using high-quality demonstrations to improve initialization and structured reasoning; then, Group Relative Policy Optimization (GRPO) algorithm, guided by a composite reward that considers goal accuracy, reasoning quality, and format compliance, to enhance generalization and adaptability. Furthermore, FlightGPT introduces a Chain-of-Thought (CoT)-based reasoning mechanism to improve decision interpretability. Extensive experiments on the city-scale dataset CityNav demonstrate that FlightGPT achieves state-of-the-art performance across all scenarios, with a 9.22\% higher success rate than the strongest baseline in unseen environments. Our implementation is publicly available.

cs.CL↗

arXiv2025

DFF: Decision-Focused Fine-tuning for Smarter Predict-then-Optimize with Limited Data

Decision-focused learning (DFL) offers an end-to-end approach to the predict-then-optimize (PO) framework by training predictive models directly on decision loss (DL), enhancing decision-making performance within PO contexts. However, the implementation of DFL poses distinct challenges. Primarily, DL can result in deviation from the physical significance of the predictions under limited data. Additionally, some predictive models are non-differentiable or black-box, which cannot be adjusted using gradient-based methods. To tackle the above challenges, we propose a novel framework, Decision-Focused Fine-tuning (DFF), which embeds the DFL module into the PO pipeline via a novel bias correction module. DFF is formulated as a constrained optimization problem that maintains the proximity of the DL-enhanced model to the original predictive model within a defined trust region. We theoretically prove that DFF strictly confines prediction bias within a predetermined upper bound, even with limited datasets, thereby substantially reducing prediction shifts caused by DL under limited data. Furthermore, the bias correction module can be integrated into diverse predictive models, enhancing adaptability to a broad range of PO tasks. Extensive evaluations on synthetic and real-world datasets, including network flow, portfolio optimization, and resource allocation problems with different predictive models, demonstrate that DFF not only improves decision performance but also adheres to fine-tuning constraints, showcasing robust adaptability across various scenarios.

cs.LG↗