arXiv subjects

Yan Jiao

Publications and source records attributed to Yan Jiao.

14 recordsLinked to original sources

arXiv2026

Dynamic Airspace Management for UAVs in Evolving Urban Environments: Collaborative Coordination and Human Safety

The low-altitude economy is an emerging industry with significant development potential, in which the safety of unmanned aerial vehicle (UAV) operations is a critical challenge. Particularly within complex urban topographies and human-populated environments, UAV airspace management must prioritize collision avoidance and human safety. We propose Pharos, a collaborative multi-UAV airspace management system. Pharos lies between the distributed local perception paradigm and the centralized fine-grained control paradigm. Pharos coordinates the safe parallel execution of UAVs in shared airspace while innovatively accounting for the impact of human fear. Pharos is implemented using the MAPPO algorithm due to its faster convergence and higher rewards than other typical MARL algorithms (HAPPO and HATRPO). To evaluate Pharos, we developed a 3D simulation system using real urban data. Visualization results demonstrate its effective airspace coordination capability. Regarding performance verification, Pharos reduced human fear by 52.72% compared to the benchmark Ipopt. Moreover, we designed spatial entropy as a system evaluation metric to quantify space utilization, which improved performance by 70.82% and 2.03% compared to the benchmarks Ipopt and A-star, respectively. The source code is available at an anonymized repository: https://github.com/pharos-anonymized/source-code.git.

cs.MA↗

arXiv2026

Sensor-Conditioned Representation Learning via Scene-Relevant Observation Quotients

Learned representations in intelligent sensing systems are often evaluated by reconstruction fidelity or downstream prediction accuracy, but these criteria do not specify which latent distinctions are justified by the sensing process. In sensor-conditioned environments, nuisance factors can change measurements without changing the scene, while distinct scenes may be indistinguishable under limited sensing capability. This paper formulates sensor-conditioned representation correctness as preserving sensing-supported scene distinctions while suppressing nuisance-induced and sensor-unsupported variation. We introduce the scene-relevant observation quotient, a representation target induced by sensing-supported distinguishability after nuisance canonicalization, and develop Observation-Quotient Tucker-Structured Autoencoding (OQ-TSAE), a scene-nuisance factorized framework with diagnostics for false distinction, false merge, nuisance sensitivity, and latent ordering consistency. Experiments on a controlled benchmark show that quotient-consistent supervision improves representation-correctness diagnostics over reconstruction-oriented, metric-learning, and contrastive-learning baselines. Sensitivity, perturbation, and ablation studies show the importance of quotient-aligned supervision, reliable quotient relations, and quotient geometry. Complementary real-radar experiments show that a reconstruction-only OQ-TSAE variant retains competitive downstream utility, robustness under observation degradation, and low seed-to-seed variability. These results suggest that sensor-conditioned representations should be evaluated not only by predictive utility, but also by whether their latent geometry preserves sensing-justified scene distinctions.

cs.AI↗

arXiv2026

AeroMesa: Efficient Data Management System for Multi-Dimensional Spatio-Temporal Trajectories

The proliferation of multi-dimensional trajectory data, fueled by large-scale IoT and the emerging low-altitude economy, particularly UAV operations, drives repositories to jointly support (x,y), (x,y,t), (x,y,z), and (x,y,z,t) queries within a single storage framework. Yet existing HBase-based systems fall short in three respects: severe row-key interval fragmentation when altitude is jointly encoded with horizontal coordinates, locality-unfriendly spatial encodings with workload-blind shape-code ordering, and coarse-grained temporal indexes that leave intra-slot boundary ambiguity unresolved. We present AeroMesa, an efficient data management system for multi-dimensional spatio-temporal trajectories built on Apache HBase and Redis, that natively supports (x,y), (x,y,t), (x,y,z), and (x,y,z,t) queries within a unified storage framework. AeroMesa addresses the above limitations through three designs: a decoupled horizontal-altitude architecture with a multi-granularity Height Spatio-Temporal Index (HTSI) that eliminates joint encoding fragmentation; Hilbert-BFS with Workload-Aware Jaccard (WAJ) reordering that improves spatial locality; and TI+, a dual-offset temporal index that resolves intra-slot false positives. Evaluations on T-Drive and an 87,537-trajectory high-fidelity UAV simulation demonstrate that AeroMesa reduces 3D/4D query latency by up to 30x over XZ3/TXZ3, lowers 2D latency by up to 17.9% over TMan, and cuts temporal candidates by up to 51.3% over MCTM, with sub-linear scalability confirmed under 200x data expansion, confirming AeroMesa's efficiency for multi-dimensional spatio-temporal trajectory management.

cs.DB↗

arXiv2026

Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning

Cross-domain knowledge alignment is essential for integrating heterogeneous medical systems, yet existing approaches typically treat entity alignment as a static matching problem, ignoring query context and cross-system asymmetry. This limitation is particularly critical in integrative medical settings, where correspondence between concepts is inherently context-dependent, non-bijective, and direction-sensitive. In this paper, we propose Query-Conditioned Entity Alignment (QCEA), which reformulates entity alignment as a query-conditioned correspondence problem. Instead of learning a fixed mapping between entity representations, QCEA treats the textual description of a source entity as a query and ranks candidate entities in the target graph, enabling context-dependent alignment. The framework integrates semantic encoding, graph-based representation learning, and a direction-aware transformation module to capture asymmetric and many-to-many correspondence across heterogeneous knowledge systems. We evaluate QCEA on TCM--WM knowledge graphs derived from SymMap, covering both symptom alignment and herb--molecule alignment tasks. Experimental results show consistent improvements over representative baselines, particularly on rank-sensitive metrics such as Hit@K and MRR. Furthermore, downstream retrieval-augmented generation (RAG) experiments demonstrate that improved alignment leads to better evidence retrieval, stronger grounding, and higher answer accuracy. These findings highlight that alignment is not merely a data integration step, but a key factor that shapes knowledge accessibility and reliability in cross-system medical reasoning.

cs.AI↗

arXiv2026

CAST: Modeling Visual State Transitions for Consistent Video Retrieval

As video content creation shifts toward long-form narratives, composing short clips into coherent storylines becomes increasingly important. However, prevailing retrieval formulations remain context-agnostic at inference time, prioritizing local semantic alignment while neglecting state and identity consistency. To address this structural limitation, we formalize the task of Consistent Video Retrieval (CVR) and introduce a diagnostic benchmark spanning YouCook2, COIN, and CrossTask. We propose CAST (Context-Aware State Transition), a lightweight, plug-and-play adapter compatible with diverse frozen vision-language embedding spaces. By predicting a state-conditioned residual update ($\Delta$) from visual history, CAST introduces an explicit inductive bias for latent state evolution. Extensive experiments show that CAST improves performance on YouCook2 and CrossTask, remains competitive on COIN, and consistently outperforms zero-shot baselines across diverse foundation backbones. Furthermore, CAST provides a useful reranking signal for black-box video generation candidates (e.g., from Veo), promoting more temporally coherent continuations.

cs.CV↗

arXiv2026

Knowledization: Claim-Level Epistemic Control with Admissibility, Source Support, and Real-World Proxy Boundaries

Near field mmWave sensing is poised to play a key role in future wireless systems, enabling environment-aware, embodied, and application adaptive operation under stringent form-factor and hardware constraints. However, achieving high spatial resolution in the near field typically requires large antenna arrays, multiple radio frequency (RF) chains, or mechanical scanning, creating a fundamental tension between spatial observability and system simplicity. This paper presents frequency as aperture clip on antenna fabric (FaACAF), a hardware efficient sensing by design architecture that synthesizes spatial aperture through the FaA paradigm using a single RF chain. FaACAF realizes a modular clip on aperture fabric, in which frequency selective clip on modules (CMs) are attached to a shared guided-wave substrate and implicitly coordinated by the instantaneous frequency modulated continuous wave (FMCW) excitation frequency. In this fabric, FMCW signaling simultaneously indexes the sensing aperture and orchestrates uplink/downlink signal distribution and echo multiplexing in a switch free, fully passive, and all analog manner, eliminating RF switching and multichannel front ends. An online self calibration mechanism stabilizes the frequency to aperture mapping under practical attachment variability without requiring full matrix calibration. Two case studies illustrate the robustness of the proposed approach and quantify the predictable sensing margin tradeoffs introduced by modular deployment. Overall, FaACAF demonstrates that near field spatial observability can be scaled through architectural coordination in the frequency domain rather than hardware expansion, providing a reconfigurable and hardware efficient pathway toward embodied sensing and integrated sensing and communication (ISAC) in future wireless systems.

cs.IT↗

arXiv2026

Task-Aware Identifiability: Observation Quotients, Statistical Geometry, and Representation Accessibility

Intelligent systems often assume observations contain the information required for a task. This fails struc- turally when a declared mechanism assigns identical ob- servation laws to latent states the task must distin- guish. We develop a unified diagnostic framework con- necting observation-induced equivalence, task identifia- bility, local statistical geometry, representation accessi- bility, and achievable risk. Its organizing condition is a standard factorization property: the observation parti- tion refines the task partition, and conditionally iid rep- etitions of that fixed channel cannot recover an exactly collapsed distinction. On regular quotient strata, Fisher geometry and nuisance-efficient Fisher information char- acterize first-order local resolvability. For representa- tions, we distinguish law-valued encoder experiments from deterministic quotient embeddings and exact task sufficiency from scale-controlled decoder accessibility. We organize task risk into structural, finite-observation, representation-channel, and learning gaps. Controlled synthetic studies validate these layers; a physics-based synthetic near-field model yields sharply different range and angle information, while NYUv2 shows persistent, decoder-modulated task preferences among frozen en- coders under two pointwise probes. TAI thereby local- izes whether task-relevant information is absent at ob- servation, weakly resolved, lost or poorly accessible in representation, or left to the learner.

cs.AR↗

arXiv2025

Epistemic Memory: A Validity Layer for Self-Maintaining Intelligent Systems

AI memory mechanisms primarily focus on preserving information content, often neglecting the validity conditions under which knowledge remains applicable, leading to semantic coordinate drift when agents move, change sensors, or encounter novel environments. This paper proposes epistemic memory as a validity-maintenance layer that governs when stored knowledge remains applicable. We formalize the dynamic epistemic quotient, an observation-induced equivalence structure over hypotheses that evolves with an agent's interaction history and sensing capabilities. We derive a pairwise incompatibility lower bound showing that any fixed semantic representation must incur unavoidable error across changing epistemic boundaries. We further identify a failure mode under symmetric crossing quotients, where overlap-based class-level transport becomes independent of pre-transition belief, motivating preservation of within-class hypothesis provenance. We introduce Observable Belief Memory (OBM) as a constructive epistemic governance architecture, combining the current epistemic quotient, belief over quotient classes, and within-class provenance through a posterior-consistent update. Controlled experiments demonstrate that explicit epistemic tracking improves robustness under changing observation conditions, particularly when class-level correspondence becomes insufficient. These results suggest that self-maintaining intelligent systems may benefit from reasoning not only about hidden states, but also about the evolving validity of the representations through which those states become knowable.

cs.LG↗

arXiv2021

Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning

We present a new practical framework based on deep reinforcement learning and decision-time planning for real-world vehicle repositioning on ride-hailing (a type of mobility-on-demand, MoD) platforms. Our approach learns the spatiotemporal state-value function using a batch training algorithm with deep value networks. The optimal repositioning action is generated on-demand through value-based policy search, which combines planning and bootstrapping with the value networks. For the large-fleet problems, we develop several algorithmic features that we incorporate into our framework and that we demonstrate to induce coordination among the algorithmically-guided vehicles. We benchmark our algorithm with baselines in a ride-hailing simulation environment to demonstrate its superiority in improving income efficiency meausred by income-per-hour. We have also designed and run a real-world experiment program with regular drivers on a major ride-hailing platform. We have observed significantly positive results on key metrics comparing our method with experienced drivers who performed idle-time repositioning based on their own expertise.

cs.LG↗

arXiv2019

Deep Reinforcement Learning for Multi-Driver Vehicle Dispatching and Repositioning Problem

Order dispatching and driver repositioning (also known as fleet management) in the face of spatially and temporally varying supply and demand are central to a ride-sharing platform marketplace. Hand-crafting heuristic solutions that account for the dynamics in these resource allocation problems is difficult, and may be better handled by an end-to-end machine learning method. Previous works have explored machine learning methods to the problem from a high-level perspective, where the learning method is responsible for either repositioning the drivers or dispatching orders, and as a further simplification, the drivers are considered independent agents maximizing their own reward functions. In this paper we present a deep reinforcement learning approach for tackling the full fleet management and dispatching problems. In addition to treating the drivers as individual agents, we consider the problem from a system-centric perspective, where a central fleet management agent is responsible for decision-making for all drivers.

cs.LG↗

arXiv2019

Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching

Improving the efficiency of dispatching orders to vehicles is a research hotspot in online ride-hailing systems. Most of the existing solutions for order-dispatching are centralized controlling, which require to consider all possible matches between available orders and vehicles. For large-scale ride-sharing platforms, there are thousands of vehicles and orders to be matched at every second which is of very high computational cost. In this paper, we propose a decentralized execution order-dispatching method based on multi-agent reinforcement learning to address the large-scale order-dispatching problem. Different from the previous cooperative multi-agent reinforcement learning algorithms, in our method, all agents work independently with the guidance from an evaluation of the joint policy since there is no need for communication or explicit cooperation between agents. Furthermore, we use KL-divergence optimization at each time step to speed up the learning process and to balance the vehicles (supply) and orders (demand). Experiments on both the explanatory environment and real-world simulator show that the proposed method outperforms the baselines in terms of accumulated driver income (ADI) and Order Response Rate (ORR) in various traffic environments. Besides, with the support of the online platform of Didi Chuxing, we designed a hybrid system to deploy our model.

cs.MA↗

arXiv2019

CoRide: Joint Order Dispatching and Fleet Management for Multi-Scale Ride-Hailing Platforms

How to optimally dispatch orders to vehicles and how to tradeoff between immediate and future returns are fundamental questions for a typical ride-hailing platform. We model ride-hailing as a large-scale parallel ranking problem and study the joint decision-making task of order dispatching and fleet management in online ride-hailing platforms. This task brings unique challenges in the following four aspects. First, to facilitate a huge number of vehicles to act and learn efficiently and robustly, we treat each region cell as an agent and build a multi-agent reinforcement learning framework. Second, to coordinate the agents from different regions to achieve long-term benefits, we leverage the geographical hierarchy of the region grids to perform hierarchical reinforcement learning. Third, to deal with the heterogeneous and variant action space for joint order dispatching and fleet management, we design the action as the ranking weight vector to rank and select the specific order or the fleet management destination in a unified formulation. Fourth, to achieve the multi-scale ride-hailing platform, we conduct the decision-making process in a hierarchical way where a multi-head attention mechanism is utilized to incorporate the impacts of neighbor agents and capture the key agent in each scale. The whole novel framework is named as CoRide. Extensive experiments based on multiple cities real-world data as well as analytic synthetic data demonstrate that CoRide provides superior performance in terms of platform revenue and user experience in the task of city-wide hybrid order dispatching and fleet management over strong baselines.

cs.MA↗

arXiv2019

Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning

A fundamental question in any peer-to-peer ridesharing system is how to, both effectively and efficiently, dispatch user's ride requests to the right driver in real time. Traditional rule-based solutions usually work on a simplified problem setting, which requires a sophisticated hand-crafted weight design for either centralized authority control or decentralized multi-agent scheduling systems. Although recent approaches have used reinforcement learning to provide centralized combinatorial optimization algorithms with informative weight values, their single-agent setting can hardly model the complex interactions between drivers and orders. In this paper, we address the order dispatching problem using multi-agent reinforcement learning (MARL), which follows the distributed nature of the peer-to-peer ridesharing problem and possesses the ability to capture the stochastic demand-supply dynamics in large-scale ridesharing scenarios. Being more reliable than centralized approaches, our proposed MARL solutions could also support fully distributed execution through recent advances in the Internet of Vehicles (IoV) and the Vehicle-to-Network (V2N). Furthermore, we adopt the mean field approximation to simplify the local interactions by taking an average action among neighborhoods. The mean field approximation is capable of globally capturing dynamic demand-supply variations by propagating many local interactions between agents and the environment. Our extensive experiments have shown the significant improvements of MARL order dispatching algorithms over several strong baselines on the gross merchandise volume (GMV), and order response rate measures. Besides, the simulated experiments with real data have also justified that our solution can alleviate the supply-demand gap during the rush hours, thus possessing the capability of reducing traffic congestion.

cs.MA↗

arXiv2017

Modeling of the Latent Embedding of Music using Deep Neural Network

While both the data volume and heterogeneity of the digital music content is huge, it has become increasingly important and convenient to build a recommendation or search system to facilitate surfacing these content to the user or consumer community. Most of the recommendation models fall into two primary species, collaborative filtering based and content based approaches. Variants of instantiations of collaborative filtering approach suffer from the common issues of so called "cold start" and "long tail" problems where there is not much user interaction data to reveal user opinions or affinities on the content and also the distortion towards the popular content. Content-based approaches are sometimes limited by the richness of the available content data resulting in a heavily biased and coarse recommendation result. In recent years, the deep neural network has enjoyed a great success in large-scale image and video recognitions. In this paper, we propose and experiment using deep convolutional neural network to imitate how human brain processes hierarchical structures in the auditory signals, such as music, speech, etc., at various timescales. This approach can be used to discover the latent factor models of the music based upon acoustic hyper-images that are extracted from the raw audio waves of music. These latent embeddings can be used either as features to feed to subsequent models, such as collaborative filtering, or to build similarity metrics between songs, or to classify music based on the labels for training such as genre, mood, sentiment, etc.

cs.SD↗