arXiv subjects

Ting Bai

Publications and source records attributed to Ting Bai.

At least 19 recordsLinked to original sources

arXiv2026

Complex VAE with Heavy-Tailed Likelihood for Radar Target Detection in Sea Clutter

To address the heavy-tailed, spike-prone nature of sea clutter and the scarcity of labeled target data, an unsupervised complex-valued variational autoencoder (VAE) for maritime radar target detection is proposed. In implementation, each complex baseband slow-time sequence is represented by its in-phase and quadrature components, and the model learns their joint reconstruction from clutter-only data. A Student-$t$ negative log-likelihood is adopted to capture heavy-tailed reconstruction errors while reducing sensitivity to outliers during clutter learning. In addition, a time-domain amplitude error constraint is introduced to penalize slow-time magnitude mismatch in the reconstruction. At inference, reconstruction deviation is used as the detection statistic, and the decision threshold is set via an empirical quantile estimated from a clutter-only validation set to enforce a constant false-alarm rate (CFAR). Experiments on measured sea-clutter data show that detection performance is consistently improved over MF, AMF, and a real-valued $\beta$-VAE under CFAR constraints.

eess.SP↗

arXiv2026

Rollout-Based Charging Scheduling for Electric Truck Fleets in Large Transportation Networks

In this paper, we investigate the charging scheduling optimization problem for large electric truck fleets operating with dedicated charging infrastructure. A central coordinator jointly determines the charging sequence and power allocation of each truck to minimize the total operational cost of the fleet. The problem is inherently combinatorial and nonlinear due to the coupling between discrete sequencing decisions and continuous charging control, rendering exact optimization intractable for real-time implementation. To address this challenge, we propose a rollout-based dynamic programming framework built upon an inner-outer two-layer structure, which decouples ordering decisions from the schedule optimization, thus enabling efficient policy evaluation and approximation. The proposed method achieves near-optimal solutions with polynomial-time complexity and adapts to dynamic arrivals and time-varying electricity prices. Simulation studies show that the rollout-based approach significantly outperforms conventional heuristics with high computational efficiency, demonstrating its effectiveness and practical applicability for real-time charging management in large-scale transportation networks.

eess.SY↗

arXiv2026

Battery Discharge Modeling for Electric Vehicles: A Hybrid Physics-based Residual Learning Approach

The growing integration of electric vehicle (EV) fleets into transportation services and energy systems requires accurate modeling of battery discharge and state-of-charge (SoC) evolution to ensure reliable vehicle operation and grid coordination. Existing approaches face a trade-off between interpretable but simplified physics-based models and data-driven methods that demand large datasets and may lack physical consistency. In this paper, we propose a hybrid physics-based residual learning framework for EV battery discharge modeling. A vehicle dynamics model based on force-balance equations provides an interpretable baseline estimate of energy consumption and SoC evolution, capturing aerodynamic drag, rolling resistance, and regenerative braking. A neural network residual learner then corrects discrepancies caused by complex factors such as traffic conditions and driver behavior. Experimental results on $1,500$ trip scenarios demonstrate that the proposed approach reduces the mean absolute percentage error to approximately $0.8\%$, significantly outperforming physics-only models while preserving physical interpretability and computational efficiency.

eess.SY↗

arXiv2026

Predictive Lane-Change and Routing Coordination in Bus-Priority Mixed Traffic Corridors

In this paper, we investigate the coordination of vehicle maneuvers in mixed-traffic corridors where connected and automated vehicles, human-driven vehicles, and buses interact under dedicated bus lane operations. We develop a segment-based network coordination framework that jointly optimizes lane-change and routing decisions of connected and automated vehicles to improve dedicated lane utilization while preserving bus priority. The proposed framework incorporates a predictive bus-protection mechanism that restricts vehicle access to protected lane segments within a monitoring horizon, together with a utility-driven lane-change strategy that accounts for anticipated travel time gains, downstream routing feasibility, and lane-change stability. By explicitly coupling network-level routing decisions with lane-level interaction control, the method proactively mitigates conflicts on dedicated lanes before congestion effects materialize. The proposed approach is evaluated through microscopic traffic simulations in SUMO using a realistic urban corridor. Simulation results demonstrate that the framework enhances bus schedule adherence and reduces average travel times for both automated and human-driven vehicles, while maintaining stable lane-change behavior without increasing maneuver frequency.

eess.SY↗

arXiv2025

LightSearcher: Efficient DeepSearch via Experiential Memory

DeepSearch paradigms have become a core enabler for deep reasoning models, allowing them to invoke external search tools to access up-to-date, domain-specific knowledge beyond parametric boundaries, thereby enhancing the depth and factual reliability of reasoning. Building upon this foundation, recent advances in reinforcement learning (RL) have further empowered models to autonomously and strategically control search tool usage, optimizing when and how to query external knowledge sources. Yet, these RL-driven DeepSearch systems often reveal a see-saw trade-off between accuracy and efficiency-frequent tool invocations can improve factual correctness but lead to unnecessary computational overhead and diminished efficiency. To address this challenge, we propose LightSearcher, an efficient RL framework that incorporates textual experiential memory by learning contrastive reasoning trajectories to generate interpretable summaries of successful reasoning patterns. In addition, it employs an adaptive reward shaping mechanism that penalizes redundant tool calls only in correct-answer scenarios. This design effectively balances the inherent accuracy-efficiency trade-off in DeepSearch paradigms. Experiments on four multi-hop QA benchmarks show that LightSearcher maintains accuracy comparable to SOTA baseline ReSearch, while reducing search tool invocations by 39.6%, inference time by 48.6%, and token consumption by 21.2%, demonstrating its superior efficiency.

cs.AI↗

arXiv2025

Optimal Platoon Formation and Stable Benefit Allocation in Mixed-Energy Truck Fleets under Size Limitations

In this paper, we investigate cooperative platoon formation and benefit allocation in mixed-energy truck fleets composed of both electric and fuel-powered trucks. The central challenge arises from the platoon-size constraint, which limits the number of trucks permitted in each platoon and introduces combinatorial coupling into the search for optimal platoon formation structures. We formulate this problem as a coalitional game with bounded coalition sizes and derive a closed-form characterization of the optimal coalition structure that maximizes the fleet-wide platooning benefit. Building on this structure, we develop a type-based least-core payoff allocation scheme that guarantees stability within the coalition-structure core (CS-core). For cases in which the CS-core is empty, we compute the least-core radius to determine the minimal relaxation required to achieve approximate stability. Through numerical studies, we demonstrate that the proposed framework consistently achieves the highest total platooning benefit among all feasible formation configurations while providing stable benefit allocations that outperform existing baseline methods.

eess.SY↗

arXiv2025

A Hybrid Physics-Based and Reinforcement Learning Framework for Electric Vehicle Charging Time Prediction

In this paper, we develop a hybrid prediction framework for accurate electric vehicle (EV) charging time estimation, a capability that is critical for trip planning, user satisfaction, and efficient operation of charging infrastructure. We combine a physics-based analytical model with a reinforcement learning (RL) approach. The analytical component captures the nonlinear constant-current/constant-voltage (CC--CV) charging dynamics and explicitly models state-of-health (SoH)--dependent capacity and power fade, providing a reliable baseline when historical data are limited. Building on this foundation, we introduce an RL component that progressively refines charging-time predictions as operational data accumulate, enabling improved long-term adaptation. Both models incorporate SoH degradation to maintain predictive accuracy over the battery lifetime. We evaluate the framework using $5{,}000$ simulated charging sessions calibrated to manufacturer specifications and publicly available EV charging datasets. Our results show that the analytical model achieves $R^{2}=98.5\%$ and $\mathrm{MAPE}=2.1\%$, while the RL model further improves performance to $R^{2}=99.2\%$ and $\mathrm{MAPE}=1.6\%$, corresponding to a $23\%$ accuracy gain and $35\%$ improved robustness to battery aging.

eess.SY↗

arXiv2025

C$^2$-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models

The attribution technique enhances the credibility of LLMs by adding citations to the generated sentences, enabling users to trace back to the original sources and verify the reliability of the output. However, existing instruction-tuned attributed LLMs often fail to properly interpret the contextual semantics of citation symbols (e.g., [i]) during text generation. This shortcoming arises from their insufficient awareness of the context information surrounding citation markers, which in turn leads to disjointed references and poor integration of retrieved knowledge into the generated content. To address this issue, we propose a novel \textbf{C}ontextual-aware \textbf{C}itation generation framework (\textbf{C$^2$}-\textbf{Cite}) that explicitly integrates the semantic relationships between citation markers and their referenced content. Specifically, a contextual citation alignment mechanism is adopted: it first encodes the retrieved document contexts into the symbol representation of citations, then aligns the marker numbers by decoding information from a citation router function. This mechanism enables the transformation of citation markers from generic placeholders into active knowledge pointers that link to the referenced source information. Experimental results on the ALCE benchmark across three datasets validate our framework C$^2$-Cite++: it outperforms the SOTA baseline by an average of 5.8\% in citation quality and 17.4\% in response correctness. The implementation is publicly available at https://github.com/BAI-LAB/c2cite

cs.IR↗

arXiv2025

Spatiotemporal Forecasting of Incidents and Congestion with Implications for Sustainable Traffic Control

Urban traffic anomalies, such as collisions and disruptions, threaten the safety, efficiency, and sustainability of transportation systems. In this paper, we present a simulation-based framework for modeling, detecting, and predicting such anomalies in urban networks. Using the Simulation of Urban MObility (SUMO) platform, we generate reproducible rear-end and intersection crash scenarios with matched baselines, enabling controlled experimentation and comparative evaluation. We record vehicle-level travel time, speed, and emissions for both edge- and network-level analysis. Building on this dataset, we develop a hybrid forecasting architecture that combines bidirectional long short-term memory networks with a diffusion convolutional recurrent neural network to capture temporal dynamics and spatial dependencies. Our simulation studies on the Broadway corridor in New York City demonstrate the framework's ability to reproduce consistent incident conditions, quantify their effects, and provide accurate multi-horizon traffic forecasts. Our results highlight the value of combining controlled anomaly generation with deep predictive models to support reproducible evaluation and sustainable traffic management.

eess.SY↗

arXiv2025

Self-Evolving LLMs via Continual Instruction Tuning

In real-world industrial settings, large language models (LLMs) must learn continually to keep pace with diverse and evolving tasks, requiring self-evolution to refine knowledge under dynamic data distributions. However, existing continual learning (CL) approaches, such as replay and parameter isolation, often suffer from catastrophic forgetting: training on new tasks degrades performance on earlier ones by overfitting to the new distribution and weakening generalization.We propose MoE-CL, a parameter-efficient adversarial mixture-of-experts framework for industrial-scale, self-evolving continual instruction tuning of LLMs. MoE-CL uses a dual-expert design: (1) a dedicated LoRA expert per task to preserve task-specific knowledge via parameter independence, mitigating forgetting; and (2) a shared LoRA expert to enable cross-task transfer. To prevent transferring task-irrelevant noise through the shared pathway, we integrate a task-aware discriminator within a GAN. The discriminator encourages the shared expert to pass only task-aligned information during sequential training. Through adversarial learning, the shared expert acquires generalized representations that mimic the discriminator, while dedicated experts retain task-specific details, balancing knowledge retention and cross-task generalization and thereby supporting self-evolution.Extensive experiments on the public MTL5 benchmark and an industrial Tencent3 benchmark validate the effectiveness of MoE-CL for continual instruction tuning. In real-world A/B testing for content compliance review on the Tencent Video platform, MoE-CL reduced manual review costs by 15.3%. These results demonstrate that MoE-CL is practical for large-scale industrial deployment where continual adaptation and stable transfer are critical.

cs.LG↗

arXiv2025

Stable and Fair Benefit Allocation in Mixed-Energy Truck Platooning: A Coalitional Game Approach

This paper addresses the benefit allocation in a mixed-energy truck platoon composed of fuel-powered and electric trucks. The interactions among trucks during platoon formation are modeled as a coalitional game with transferable utility. We first design a stable payoff allocation scheme that accounts for truck heterogeneity in energy savings and platoon roles (leader or follower), establishing core-stability conditions to ensure that no subset of trucks has an incentive to deviate for greater benefit. To enhance payoff fairness, we then propose a closed-form, Shapley value-based allocation approach that is computationally efficient and independent of the platoon size. Sufficient conditions under which the allocation is both fair and core-stable are provided. In scenarios where the Shapley value falls outside the core, we develop an alternative allocation based on the stable payoff that minimizes the mean relative deviation from the Shapley value while preserving core stability. This deviation is further proved to be upper-bounded by $1$, showing a favorable trade-off between stability and fairness. Finally, extensive numerical studies validate the theoretical results and demonstrate the effectiveness of the proposed framework in facilitating stable, equitable, and sustainable cooperation in mixed-energy truck platooning.

eess.SY↗

arXiv2025

Memory OS of AI Agent

Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with AI agents. To overcome this challenge, we innovatively propose a Memory Operating System, i.e., MemoryOS, to achieve comprehensive and efficient memory management for AI agents. Inspired by the memory management principles in operating systems, MemoryOS designs a hierarchical storage architecture and consists of four key modules: Memory Storage, Updating, Retrieval, and Generation. Specifically, the architecture comprises three levels of storage units: short-term memory, mid-term memory, and long-term personal memory. Key operations within MemoryOS include dynamic updates between storage units: short-term to mid-term updates follow a dialogue-chain-based FIFO principle, while mid-term to long-term updates use a segmented page organization strategy. Our pioneering MemoryOS enables hierarchical memory integration and dynamic updating. Extensive experiments on the LoCoMo benchmark show an average improvement of 49.11% on F1 and 46.18% on BLEU-1 over the baselines on GPT-4o-mini, showing contextual coherence and personalized memory retention in long conversations. The implementation code is open-sourced at https://github.com/BAI-LAB/MemoryOS.

cs.AI↗

arXiv2025

A Coordinated Routing Approach for Enhancing Bus Timeliness and Travel Efficiency in Mixed-Traffic Environment

This paper proposes a coordinated routing approach that investigates the use of connected and automated vehicles (CAVs) in dedicated bus lanes. The aim is to improve bus schedule adherence while enhancing the travel efficiency of CAVs during the transitional phase of mixed traffic environments. Our approach utilizes real-time traffic data to dynamically reroute CAVs in anticipation of congestion. By continuously monitoring traffic conditions on dedicated lanes and tracking the real-time positions of buses, the system adjusts CAV routes in advance to avoid potential interference with operating buses. This cooperation reduces CAV travel times and minimizes delays that impact transit services. The proposed strategy is validated using microscopic traffic simulations in SUMO. The results demonstrate significant improvements in both transit on-time performance and CAV travel efficiency across a range of traffic conditions.

eess.SY↗

arXiv2025

Platoon Coordination and Leader Selection in Mixed Transportation Systems via Dynamic Programming

With the growing penetration of electric trucks, freight transportation is transitioning toward a mixed system comprising both fuel-powered and electric trucks. Enhancing truck platoon formation in such a heterogeneous environment presents new challenges. This paper investigates the hub-based platoon coordination problem in a mixed truck fleet, where the focus is to optimize the trucks' waiting times, charging amounts for electric trucks, and platoon leader assignments. The objective is to maximize the overall platoon revenue of the fleet while accounting for the associated waiting and charging costs. We formulate the problem as a mixed-integer linear program and present a dynamic programming approach to compute its sub-optimal solution efficiently. The proposed method operates in polynomial time, ensuring scalable computational efficiency. Simulation studies involving 1,000 trucks traveling between two hubs in Sweden demonstrate the effectiveness and scalability of the proposed approach.

math.OC↗

arXiv2025

Deviation Between Team-Optimal Solution and Nash Equilibrium in Flow Assignment Problems

We investigate the relationship between the team-optimal solution and the Nash equilibrium (NE) to assess the impact of strategy deviation on team performance. As a working use case, we focus on a class of flow assignment problems in which each source node acts as a cooperating decision maker (DM) within a team that minimizes the team cost based on the team-optimal strategy. In practice, some selfish DMs may prioritize their own marginal cost and deviate from NE strategies, thus potentially degrading the overall performance. To quantify this deviation, we explore the deviation bound between the team-optimal solution and the NE in two specific scenarios: (i) when the team-optimal solution is unique and (ii) when multiple solutions do exist. This helps DMs analyze the factors influencing the deviation and adopting the NE strategy within a tolerable range. Furthermore, in the special case of a potential game model, we establish the consistency between the team-optimal solution and the NE. Once the consistency condition is satisfied, the strategy deviation does not alter the total cost, and DMs do not face a strategic trade-off. Finally, we validate our theoretical analysis through some simulation studies.

cs.GT↗

arXiv2025

A Cooperative Compliance Control Framework for Socially Optimal Mixed Traffic Routing

In mixed traffic environments, where Connected and Autonomed Vehicles (CAVs) coexist with potentially non-cooperative Human-Driven Vehicles (HDVs), the self-centered behavior of human drivers may compromise the efficiency, optimality, and safety of the overall traffic network. In this paper, we propose a Cooperative Compliance Control (CCC) framework for mixed traffic routing, where a Social Planner (SP) optimizes vehicle routes for system-wide optimality while a compliance controller incentivizes human drivers to align their behavior with route guidance from the SP through a "refundable toll" scheme. A key challenge arises from the heterogeneous and unknown response models of different human driver types to these tolls, making it difficult to design a proper controller and achieve desired compliance probabilities over the traffic network. To address this challenge, we employ Control Lyapunov Functions (CLFs) to adaptively correct (learn) crucial components of our compliance probability model online, construct data-driven feedback controllers, and demonstrate that we can achieve the desired compliance probability for HDVs, thereby contributing to the social optimality of the traffic network.

eess.SY↗

arXiv2025

Routing Guidance for Emerging Transportation Systems with Improved Dynamic Trip Equity

This paper presents a dynamic routing guidance system that optimizes route recommendations for individual vehicles in an emerging transportation system while enhancing travelers' trip equity. We develop a framework to quantify trip quality and equity in dynamic travel environments, providing new insights into how routing guidance influences equity in road transportation. Our approach enables real-time routing by incorporating both monitored and anticipated traffic congestion. We provide conditions that ensure perfect trip equity for all travelers in a free-flow network. Simulation studies on 1,000 vehicles traversing an urban road network in Boston demonstrate that our method improves trip equity by approximately 11.4\% compared to the shortest-route strategy. In addition, the results reveal that our approach redistributes travel costs across vehicle types through route optimization, contributing to a more equitable transportation system.

eess.SY↗

arXiv2024

BaiJia: A Large-Scale Role-Playing Agent Corpus of Chinese Historical Characters

We introduce a comprehensive large-scale role-playing agent corpus, termed BaiJia, that comprises various Chinese historical characters. This corpus is noteworthy for being the pioneering compilation of low-resource data that can be utilized in large language models (LLMs) to engage in AI-driven historical role-playing agents. BaiJia addresses the challenges in terms of fragmented historical textual records in different forms and modalities, integrating various characters' information, including their biographical, literary, family relations, historical events, and so on. We conduct extensive experiments to demonstrate the effectiveness of our BaiJia agent corpus in bolstering the role-playing abilities of various foundational LLMs, and promoting the development and assessment of LLMs in the context of historical role-playing tasks. The agent corpus is available at baijia.online.

cs.AI↗