arXiv subjects

Zhenyu Gao

Publications and source records attributed to Zhenyu Gao.

At least 19 recordsLinked to original sources

arXiv2026

SuppreSensing: Expert-Guided Feature Recalibration and Discrepancy Augmentation for Multimodal Object Detection

Multimodal object detection in remote sensing faces challenges due to semantic heterogeneity and modality-specific noise interference. To this end, we propose SuppreSensing, which reformulates multimodal fusion as a selective collaboration process that jointly models shared information and modality-specific cues. SuppreSensing first designs an Expert-driven Multimodal Feature Recalibration (EMFR) module, which reformulates shared-consensus extraction as an input-adaptive multi-expert selection process to alleviate the symmetry trap in multimodal fusion. Complementing this, a modality-specific attribute augmentation strategy is employed to enhance specific modality features by modeling bidirectional discrepancy patterns, mitigating cross-modal heterogeneity. Furthermore, we propose an Expert-driven Customized Feature Purification (ECFP) module based on a "specialized inspection-comprehensive analysis-diagnostic update" physical examination paradigm to iteratively filter redundancies and reinforce task-relevant semantics. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate that SuppreSensing achieves state-of-the-art detection performance. Cross-domain evaluations on natural scene datasets (FLIR and LLVIP) further validate its superior robustness and generalization capability across diverse environmental conditions.

cs.CV↗

arXiv2026

Co-planning of Flight Corridors and Communication Infrastructure for Urban Drone Logistics Networks

Reliable wireless connectivity is essential for urban air mobility (UAM) networks in dense urban environments. It is therefore imperative to carefully plan the supporting communication infrastructure for UAM flight corridors. Most existing works optimize communication infrastructure and UAV flight paths independently, often leading to unnecessary base station (BS) deployment or excessive flight detours. This paper studies the joint optimization of BS deployment and UAV flight corridors in complex urban environments, aiming to minimize both infrastructure investment and flight distance while satisfying communication quality constraints. We propose CR-CMAB, a channel reciprocity-guided combinatorial multi-armed bandit framework. The framework constructs high-fidelity radio maps using 3D ray tracing, selects BS combinations via coverage-aware CMAB search, and dynamically expands the search space by identifying promising BS locations through channel reciprocity. Experimental results from a detailed case study demonstrate that CR-CMAB outperforms baseline methods with moderate computational time, yielding more strategically positioned BSs and shorter flight corridors. This study offers a practical planning perspective for cost-effective and communication-reliable UAM deployment in future smart cities.

cs.RO↗

arXiv2026

Can LLMs Hire Fairly? Racial Bias in Resume Screening

We audit fourteen mainstream large language models (LLMs) for hiring discrimination using the paired-resume methodology of Kline, Rose, and Walters (2022). The sole 2023-vintage model reproduces the pro-White callback gap documented in field experiments on labor market discrimination ($+2.12$ pp, significant at the 1\% level). Every model released in 2024 or after shows either a null gap or a significant pro-Black reversal (up to $-3.01$ pp). The same pattern holds on the gender axis. Based on 24,024 paired postings per model across 14 models, our results document a reversal in the direction of algorithmic hiring bias across model generations.

cs.CL↗

arXiv2026

SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring

Pilot readback of Air Traffic Control (ATC) voice instructions is a primary safeguard against miscommunication in air transportation. However, readback anomalies remain implicated in approximately 80% of aviation incidents. This vulnerability is further exacerbated by rising traffic volume and elevated cognitive workload, thereby motivating automated readback monitoring by machine. Traditional rule-based and machine learning approaches struggle to generalize across the highly variable and evolving phraseology of air traffic controller-pilot communications. While Large Language Models (LLMs) have opened a new avenue through their strong reasoning and generalization capabilities, existing approaches still face deployment and computational barriers in practice. In this work, we propose Semantic reasoning for Communication via Open-set Plug-in with Examples (SCOPE), a novel lightweight-training LLM framework that advances both the efficiency and accuracy of machine-based ATC readback monitoring. The core idea is to couple a plug-in open-set classifier with a carefully designed in-context learning mechanism on top of a frozen LLM. Extensive experiments on the semi-synthetic communication dataset show that SCOPE attains superior accuracy while delivering the low-latency response required for operational environments. Under a few-shot setting, SCOPE achieves 91.05% accuracy in open-set detection and corrects 96.63% of anomalous readbacks, thereby outperforming the strongest available baselines while providing explanations for its decisions. These findings demonstrate the potential of our framework as a practical pathway toward interpretable and controllable ATC readback monitoring.

cs.LG↗

arXiv2026

Debiasing LLMs by Fine-tuning

Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We propose a supervised fine-tuning (SFT) approach that uses Low-Rank Adaptation (LoRA) to train off-the-shelf LLMs on instruction datasets constructed from rational benchmark forecasts. By intervening at the parameter level, SFT changes how LLMs map observed information into forecasts and thereby mitigates extrapolation bias. We evaluate the fine-tuned model in two settings: controlled forecasting experiments and cross-sectional stock return prediction. In both settings, fine-tuning corrects the extrapolative bias out-of-sample, establishing a low-cost and generalizable method for debiasing LLMs.

q-fin.GN↗

arXiv2026

DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining

Large language models pretrained on internet-scale data risk lookahead bias in forecasting tasks, as they may have already seen the true outcome during training. To address this, we present DatedGPT, a family of twelve 1.3B-parameter language models trained from scratch on approximately 100 billion tokens each with strict annual data cutoffs spanning 2013 to 2024, together with DatedInstruct, an instruction dataset grounded in each year's documents to prevent leakage during post-training. The models are competitive with open models of similar scale, and perplexity-based probing confirms that each model's knowledge is bounded by its cutoff year. On stock return prediction over 61,000 firm-day news headlines, DatedGPT-instruct achieves an annualised Sharpe ratio of $3.20$ under the lookahead-bias-free setup. Lookahead-biased models, whose training data covers the outcome period, add a lookahead premium of $26.4$ b.p. per standard deviation, significant at the 1% level. The series thus enables direct analysis of lookahead bias in financial forecasting. We provide an interactive web demo that allows users to query and compare responses from models across different cutoff years, available at www.datedgpt.com.

cs.CL↗

arXiv2025

Detecting Lookahead Bias in LLM Forecasts

We develop a statistical procedure to detect lookahead bias in economic forecasts generated by large language models (LLMs). Using a date-only recall query for a firm-date pair, we estimate the probability that the LLM has internalized information about the realized outcome, a statistic we term Lookahead Propensity (LAP). LAP is materially positive throughout the in-sample period and collapses essentially to zero right after the training-data cutoff. We show that a positive interaction between LAP and the LLM forecast in an accuracy regression indicates lookahead-bias contamination, and apply the test to two forecasting tasks: news headlines predicting stock returns and earnings call transcripts predicting capital expenditures. In both applications, the LLM forecast's predictive power is amplified on high-LAP firm-date pairs, and the interaction loses significance on post-training-cutoff samples. Our test provides a cost-efficient, diagnostic tool for assessing the validity and reliability of LLM-generated forecasts.

q-fin.GN↗

arXiv2025

Integrated Noise and Safety Management in UAM via A Unified Reinforcement Learning Framework

Urban Air Mobility (UAM) envisions the widespread use of small aerial vehicles to transform transportation in dense urban environments. However, UAM faces critical operational challenges, particularly the balance between minimizing noise exposure and maintaining safe separation in low-altitude urban airspace, two potentially conflicting objectives that are often addressed separately. We propose a reinforcement learning (RL)-based air traffic management system that integrates both noise and safety considerations within a unified, decentralized framework. Under this scalable air traffic coordination solution, agents operate in a structured, multi-layered airspace and learn altitude adjustment policies to jointly manage noise impact and separation constraints. The system demonstrates strong performance across both objectives and reveals tradeoffs among separation, noise exposure, and energy efficiency under high traffic density. Among the three objectives, safe separation is accorded the highest priority, whereas the relative significance of noise and energy varies by location and is contingent upon financial and public policy considerations. The findings highlight the potential of RL and multi-objective coordination strategies in enhancing the safety, quietness, and efficiency of UAM operations.

cs.MA↗

arXiv2025

Histo-Planner: A Real-time Local Planner for MAVs Teleoperation based on Histogram of Obstacle Distribution

This paper concerns real-time obstacle avoidance for micro aerial vehicles (MAVs). Motivated by teleoperation applications in cluttered environments with limited computational power, we propose a local planner that does not require the knowledge or construction of a global map of the obstacles. The proposed solution consists of a real-time trajectory planning algorithm that relies on the histogram of obstacle distribution and a planner manager that triggers different planning modes depending on obstacles location around the MAV. The proposed solution is validated, for a teleoperation application, with both simulations and indoor experiments. Benchmark comparisons based on a designed simulation platform are also provided.

cs.RO↗

arXiv2025

Learning-based Airflow Inertial Odometry for MAVs using Thermal Anemometers in a GPS and vision denied environment

This work demonstrates an airflow inertial based odometry system with multi-sensor data fusion, including thermal anemometer, IMU, ESC, and barometer. This goal is challenging because low-cost IMUs and barometers have significant bias, and anemometer measurements are very susceptible to interference from spinning propellers and ground effects. We employ a GRU-based deep neural network to estimate relative air speed from noisy and disturbed anemometer measurements, and an observer with bias model to fuse the sensor data and thus estimate the state of aerial vehicle. A complete flight data, including takeoff and landing on the ground, shows that the approach is able to decouple the downwash induced wind speed caused by propellers and the ground effect, and accurately estimate the flight speed in a wind-free indoor environment. IMU, and barometer bias are effectively estimated, which significantly reduces the position integration drift, which is only 5.7m for 203s manual random flight. The open source is available on https://github.com/SyRoCo-ISIR/Flight-Speed-Estimation-Airflow.

cs.RO↗

arXiv2025

A Reinforcement Learning Approach to Quiet and Safe UAM Traffic Management

Urban air mobility (UAM) is a transformative system that operates various small aerial vehicles in urban environments to reshape urban transportation. However, integrating UAM into existing urban environments presents a variety of complex challenges. Recent analyses of UAM's operational constraints highlight aircraft noise and system safety as key hurdles to UAM system implementation. Future UAM air traffic management schemes must ensure that the system is both quiet and safe. We propose a multi-agent reinforcement learning approach to manage UAM traffic, aiming at both vertical separation assurance and noise mitigation. Through extensive training, the reinforcement learning agent learns to balance the two primary objectives by employing altitude adjustments in a multi-layer UAM network. The results reveal the tradeoffs among noise impact, traffic congestion, and separation. Overall, our findings demonstrate the potential of reinforcement learning in mitigating UAM's noise impact while maintaining safe separation using altitude adjustments

cs.MA↗

arXiv2024

Noise-Aware and Equitable Urban Air Traffic Management: An Optimization Approach

Urban air mobility (UAM), a transformative concept for the transport of passengers and cargo, faces several integration challenges in complex urban environments. Community acceptance of aircraft noise is among the most noticeable of these challenges when launching or scaling up a UAM system. Properly managing community noise is fundamental to establishing a UAM system that is environmentally and socially sustainable. In this work, we develop a holistic and equitable approach to manage UAM air traffic and its community noise impact in urban environments. The proposed approach is a hybrid approach that considers a mix of different noise mitigation strategies, including limiting the number of operations, cruising at higher altitudes, and ambient noise masking. We tackle the problem through the lens of network system control and formulate a multi-objective optimization model for managing traffic flow in a multi-layer UAM network while concurrently pursuing demand fulfillment, noise control, and energy saving. Further, we use a social welfare function in the optimization model as the basis for the efficiency-fairness trade-off in both demand fulfillment and noise control. We apply the proposed approach to a comprehensive case study in the city of Austin and perform design trade-offs through both visual and quantitative analyses.

eess.SY↗

arXiv2023

Developing 3D Virtual Safety Risk Terrain for UAS Operations in Complex Urban Environments

Unmanned Aerial Systems (UAS), an integral part of the Advanced Air Mobility (AAM) vision, are capable of performing a wide spectrum of tasks in urban environments. The societal integration of UAS is a pivotal challenge, as these systems must operate harmoniously within the constraints imposed by regulations and societal concerns. In complex urban environments, UAS safety has been a perennial obstacle to their large-scale deployment. To mitigate UAS safety risk and facilitate risk-aware UAS operations planning, we propose a novel concept called \textit{3D virtual risk terrain}. This concept converts public risk constraints in an urban environment into 3D exclusion zones that UAS operations should avoid to adequately reduce risk to Entities of Value (EoV). To implement the 3D virtual risk terrain, we develop a conditional probability framework that comprehensively integrates most existing basic models for UAS ground risk. To demonstrate the concept, we build risk terrains on a Chicago downtown model and observe their characteristics under different conditions. We believe that the 3D virtual risk terrain has the potential to become a new routine tool for risk-aware UAS operations planning, urban airspace management, and policy development. The same idea can also be extended to other forms of societal impacts, such as noise, privacy, and perceived risk.

cs.CE↗

arXiv2023

Alpha-Fair Routing in Urban Air Mobility with Risk-Aware Constraints

In the vision of urban air mobility, air transport systems serve the demands of urban communities by routing flight traffic in networks formed by vertiports and flight corridors. We develop a routing algorithm to ensure that the air traffic flow fairly serves the demand of multiple communities subject to stochastic network capacity constraints. This algorithm guarantees that the flight traffic volume allocated to different communities satisfies the \emph{alpha-fairness conditions}, a commonly used family of fairness conditions in resource allocation. It further ensures robust satisfaction of stochastic network capacity constraints by bounding the coherent risk measures of capacity violation. We prove that implementing the proposed algorithm is equivalent to solving a convex optimization problem. We demonstrate the proposed algorithm using a case study based on the city of Austin. Compared with one that maximizes the total served demands, the proposed algorithm promotes even distributions of served demands for different communities.

math.OC↗

arXiv2023

Class Binarization to NeuroEvolution for Multiclass Classification

Multiclass classification is a fundamental and challenging task in machine learning. The existing techniques of multiclass classification can be categorized as (i) decomposition into binary (ii) extension from binary and (iii) hierarchical classification. Decomposing multiclass classification into a set of binary classifications that can be efficiently solved by using binary classifiers, called class binarization, which is a popular technique for multiclass classification. Neuroevolution, a general and powerful technique for evolving the structure and weights of neural networks, has been successfully applied to binary classification. In this paper, we apply class binarization techniques to a neuroevolution algorithm, NeuroEvolution of Augmenting Topologies (NEAT), that is used to generate neural networks for multiclass classification. We propose a new method that applies Error-Correcting Output Codes (ECOC) to design the class binarization strategies on the neuroevolution for multiclass classification. The ECOC strategies are compared with the class binarization strategies of One-vs-One and One-vs-All on three well-known datasets Digit, Satellite, and Ecoli. We analyse their performance from four aspects of multiclass classification degradation, accuracy, evolutionary efficiency, and robustness. The results show that the NEAT with ECOC performs high accuracy with low variance. Specifically, it shows significant benefits in a flexible number of binary classifiers and strong robustness.

cs.LG↗

arXiv2023

Improved Aircraft Environmental Impact Segmentation via Metric Learning

Accurate modeling of aircraft environmental impact is pivotal to the design of operational procedures and policies to mitigate negative aviation environmental impact. Aircraft environmental impact segmentation is a process which clusters aircraft types that have similar environmental impact characteristics based on a set of aircraft features. This practice helps model a large population of aircraft types with insufficient aircraft noise and performance models and contributes to better understanding of aviation environmental impact. Through measuring the similarity between aircraft types, distance metric is the kernel of aircraft segmentation. Traditional ways of aircraft segmentation use plain distance metrics and assign equal weight to all features in an unsupervised clustering process. In this work, we utilize weakly-supervised metric learning and partial information on aircraft fuel burn, emissions, and noise to learn weighted distance metrics for aircraft environmental impact segmentation. We show in a comprehensive case study that the tailored distance metrics can indeed make aircraft segmentation better reflect the actual environmental impact of aircraft. The metric learning approach can help refine a number of similar data-driven analytical studies in aviation.

cs.LG↗

arXiv2023

Risk-aware Urban Air Mobility Network Design with Overflow Redundancy

Urban air mobility (UAM), as envisioned by aviation professionals, will transport passengers and cargo at low altitudes within urban and suburban areas. To operate in urban environments, precise air traffic management, in particular the management of traffic overflows due to physical and operational disruptions will be critical to ensuring system safety and efficiency. To this end, we propose UAM network design with reserve capacity, i.e., a design where alternative landing options and flight corridors are explicitly considered as a means of improving contingency management. Similar redundancy considerations are incorporated in the design of many critical infrastructures, yet remain unexploited in the air transportation literature. In our methodology, we first model how disruptions to a given UAM network might impact on the nominal traffic flow and how this flow might be re-accommodated on an extended network with reserve capacity. Then, through an optimization problem, we select the locations and capacities for the backup vertiports with the maximal expected throughput of the extended network over all possible disruption scenarios, while the throughput is the maximal amount of flights that the network can accommodate per unit of time. We show that we can obtain the solution for the corresponding bi-level and bi-linear optimization problem by solving a mixed-integer linear program. We demonstrate our methodology in the case study using networks from Milwaukee, Atlanta, and Dallas--Fort Worth metropolitan areas and show how the throughput and flexibility of the UAM networks with reserve capacity can outcompete those without.

eess.SY↗

arXiv2023

Stochastic spin-orbit-torque device as the STDP synapse for spiking neural networks

Neuromorphic hardware as a non-Von Neumann architecture has better energy efficiency and parallelism than the conventional computer. Here, with numerical modeling spin-orbit torque (SOT) device using current-induced SOT and Joule heating effects, we acquire its magnetization switching probability as a function of the input current pulses and use it to mimic the spike-timing-dependent plasticity learning behavior like actual brain working. We further demonstrate that the artificial spiking neural network (SNN) built by this SOT device can perform unsupervised handwritten digit recognition with the accuracy of 80% and logic operation learning. Our work provides a new clue to achieving SNN-based neuromorphic hardware using high-energy efficiency and nonvolatile spintronics nanodevices

physics.app-ph↗