PyTorchKR Papers

최신 논문

총 3,273편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2504.20068

Tempo: Application-aware LLM Serving with Mixed SLO Requirements

The integration of Large Language Models (LLMs) into diverse applications, ranging from interactive chatbots and cloud AIOps to intelligent agents, has introduced a wide spectrum of Service Level Objectives (SLOs) for responsiveness. These workloads include latency-sensitive requests focused on per-token latency in streaming chat, throughput-intensive requests that require rapid full responses to invoke tools, and collective requests with dynamic dependencies arising from self-reflection or agent-based reasoning. This workload diversity, amplified by unpredictable request information such as response lengths and runtime dependencies, makes existing schedulers inadequate even within their design envelopes. In this paper, we define service gain as the useful service delivered by completing requests. We observe that as SLO directly reflects the actual performance needs of requests, completing a request much faster than its SLO (e.g., deadline) yields limited additional service gain. Based on this insight, we introduce Tempo, the first systematic SLO-aware scheduler designed to maximize service gain across diverse LLM workloads. Tempo allocates just enough serving bandwidth to meet each SLO, maximizing residual capacity for others best-effort workloads. Instead of assuming request information or none at all, it adopts a hybrid scheduling strategy: using quantile-based response upper bounds and dependency-graph matching for conservative initial estimates, prioritizing requests by service gain density, and refining decisions online as generation progresses. Our evaluation across diverse workloads, including chat, reasoning, and agentic pipelines, shows that Tempo improves end-to-end service gain by up to 8.3$\times$ and achieves up to 10.3$\times$ SLO goodput compared to state-of-the-art designs

arXiv:2504.16837

Approximating Optimal Labelings for Temporal Connectivity

In a temporal graph the edge set dynamically changes over time according to a set of time-labels associated with each edge that indicates at which time-steps the edge is available. Two vertices are connected if there is a path connecting them in which the edges are traversed in increasing order of their labels. We study the problem of scheduling the availability time of the edges of a temporal graph in such a way that all pairs of vertices are connected within a given maximum allowed time $a$ and the overall number of labels is minimized. The problem, known as \emph{Minimum Aged Labeling} (MAL), has several applications in logistics, distribution scheduling, and information spreading in social networks, where carefully choosing the time-labels can significantly reduce infrastructure costs, fuel consumption, or greenhouse gases. The problem MAL has previously been proved to be NP-complete on undirected graphs and \APX-hard on directed graphs. In this paper, we extend our knowledge on the complexity and approximability of MAL in several directions. We first show that the problem cannot be approximated within a factor better than $O(\log n)$ when $a\geq 2$, unless $\text{P} = \text{NP}$, and a factor better than $2^{\log ^{1-\epsilon} n}$ when $a\geq 3$, unless $\text{NP}\subseteq \text{DTIME}(2^{\text{polylog}(n)})$, where $n$ is the number of vertices in the graph. Then we give a set of approximation algorithms that, under some conditions, almost match these lower bounds. In particular, we show that the approximation depends on a relation between $a$ and the diameter of the input graph. We further establish a connection with a foundational optimization problem on static graphs called \emph{Diameter Constrained Spanning Subgraph} (DCSS) and show that our hardness results also apply to DCSS.

arXiv:2504.15930

StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation

Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first generates samples online, which are then used to derive rewards for training. The conventional view holds that the colocated architecture, where the two stages share resources via temporal multiplexing, outperforms the disaggregated architecture, in which dedicated resources are assigned to each stage. However, in real-world deployments, we observe that the colocated architecture suffers from resource coupling, where the two stages are constrained to use the same resources. This coupling compromises the scalability and cost-efficiency of colocated RL in large-scale training. In contrast, the disaggregated architecture allows for flexible resource allocation, supports heterogeneous training setups, and facilitates cross-datacenter deployment. StreamRL is designed with disaggregation from first principles and fully unlocks its potential by addressing two types of performance bottlenecks in existing disaggregated RL frameworks: pipeline bubbles, caused by stage dependencies, and skewness bubbles, resulting from long-tail output length distributions. To address pipeline bubbles, StreamRL breaks the traditional stage boundary in synchronous RL algorithms through stream generation and achieves full overlapping in asynchronous RL. To address skewness bubbles, StreamRL employs an output-length ranker model to identify long-tail samples and reduces generation time via skewness-aware dispatching and scheduling. Experiments show that StreamRL improves throughput by up to 2.66x compared to existing state-of-the-art systems, and improves cost-effectiveness by up to 1.33x in a heterogeneous, cross-datacenter setting.

arXiv:2504.15303

High-Throughput LLM inference on Heterogeneous Clusters

Nowadays, many companies possess various types of AI accelerators, forming heterogeneous clusters. Efficiently leveraging these clusters for high-throughput large language model (LLM) inference services can significantly reduce costs and expedite task processing. However, LLM inference on heterogeneous clusters presents two main challenges. Firstly, different deployment configurations can result in vastly different performance. The number of possible configurations is large, and evaluating the effectiveness of a specific setup is complex. Thus, finding an optimal configuration is not an easy task. Secondly, LLM inference instances within a heterogeneous cluster possess varying processing capacities, leading to different processing speeds for handling inference requests. Evaluating these capacities and designing a request scheduling algorithm that fully maximizes the potential of each instance is challenging. In this paper, we propose a high-throughput inference service system on heterogeneous clusters. First, the deployment configuration is optimized by modeling the resource amount and expected throughput and using the exhaustive search method. Second, a novel mechanism is proposed to schedule requests among instances, which fully considers the different processing capabilities of various instances. Extensive experiments show that the proposed scheduler improves throughput by 122.5% and 33.6% on two heterogeneous clusters, respectively.

arXiv:2504.15299

D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving

The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead. Despite its benefits, MoE is still too expensive to deploy on resource-constrained edge devices, especially with the demands of on-device inference services. Recent research efforts often apply model compression techniques, such as quantization, pruning and merging, to restrict MoE complexity. Unfortunately, due to their predefined static model optimization strategies, they cannot always achieve the desired quality-overhead trade-off when handling multiple requests, finally degrading the on-device quality of service. These limitations motivate us to propose the D$^2$MoE, an algorithm-system co-design framework that matches diverse task requirements by dynamically allocating the most proper bit-width to each expert. Specifically, inspired by the nested structure of matryoshka dolls, we propose the matryoshka weight quantization (MWQ) to progressively compress expert weights in a bit-nested manner and reduce the required runtime memory. On top of it, we further optimize the I/O-computation pipeline and design a heuristic scheduling algorithm following our hottest-expert-bit-first (HEBF) principle, which maximizes the expert parallelism between I/O and computation queue under constrained memory budgets, thus significantly reducing the idle temporal bubbles waiting for the experts to load. Evaluations on real edge devices show that D$^2$MoE improves the overall inference throughput by up to 1.39$\times$ and reduces the peak memory footprint by up to 53% over the latest on-device inference frameworks, while still preserving comparable serving accuracy as its INT8 counterparts.

arXiv:2505.00299

Intelligent Task Scheduling for Microservices via A3C-Based Reinforcement Learning

To address the challenges of high resource dynamism and intensive task concurrency in microservice systems, this paper proposes an adaptive resource scheduling method based on the A3C reinforcement learning algorithm. The scheduling problem is modeled as a Markov Decision Process, where policy and value networks are jointly optimized to enable fine-grained resource allocation under varying load conditions. The method incorporates an asynchronous multi-threaded learning mechanism, allowing multiple agents to perform parallel sampling and synchronize updates to the global network parameters. This design improves both policy convergence efficiency and model stability. In the experimental section, a real-world dataset is used to construct a scheduling scenario. The proposed method is compared with several typical approaches across multiple evaluation metrics, including task delay, scheduling success rate, resource utilization, and convergence speed. The results show that the proposed method delivers high scheduling performance and system stability in multi-task concurrent environments. It effectively alleviates the resource allocation bottlenecks faced by traditional methods under heavy load, demonstrating its practical value for intelligent scheduling in microservice systems.

arXiv:2504.20105

Electricity Cost Minimization for Multi-Workflow Allocation in Geo-Distributed Data Centers

Worldwide, Geo-distributed Data Centers (GDCs) provide computing and storage services for massive workflow applications, resulting in high electricity costs that vary depending on geographical locations and time. How to reduce electricity costs while satisfying the deadline constraints of workflow applications is important in GDCs, which is determined by the execution time of servers, power, and electricity price. Determining the completion time of workflows with different server frequencies can be challenging, especially in scenarios with heterogeneous computing resources in GDCs. Moreover, the electricity price is also different in geographical locations and may change dynamically. To address these challenges, we develop a geo-distributed system architecture and propose an Electricity Cost aware Multiple Workflows Scheduling algorithm (ECMWS) for servers of GDCs with fixed frequency and power. ECMWS comprises four stages, namely workflow sequencing, deadline partitioning, task sequencing, and resource allocation where two graph embedding models and a policy network are constructed to solve the Markov Decision Process (MDP). After statistically calibrating parameters and algorithm components over a comprehensive set of workflow instances, the proposed algorithms are compared with the state-of-the-art methods over two types of workflow instances. The experimental results demonstrate that our proposed algorithm significantly outperforms other algorithms, achieving an improvement of over 15\% while maintaining an acceptable computational time. The source codes are available at https://gitee.com/public-artifacts/ecmws-experiments.

arXiv:2504.19867

semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a disaggregated system where the two phases are disaggregated to different GPUs. The design of the disaggregated system addresses the latency interference and sophisticated scheduling issues in the unified system but leads to storage challenges including 1) replicated weights for both phases that prevent flexible deployment, 2) KV cache transfer overhead between the two phases, 3) storage imbalance that causes substantial wasted space of the GPU capacity, and 4) suboptimal resource adjustment arising from the difficulties in migrating KV cache. Such storage inefficiency delivers poor serving performance under high request rates. In this paper, we identify that the advantage of the disaggregated system lies in the disaggregated computation, i.e., partitioning the computational resource to enable the asynchronous computation of two phases. Thus, we propose a novel LLM serving system, semi-PD, characterized by disaggregated computation and unified storage. In semi-PD, we introduce a computation resource controller to achieve disaggregated computation at the streaming multi-processor (SM) level, and a unified memory manager to manage the asynchronous memory access from both phases. semi-PD has a low-overhead resource adjustment mechanism between the two phases, and a service-level objective (SLO) aware dynamic partitioning algorithm to optimize the SLO attainment. Compared to state-of-the-art systems, semi-PD maintains lower latency at higher request rates, reducing the average end-to-end latency per request by 1.27-2.58x on DeepSeek series models, and serves 1.55-1.72x more requests adhering to latency constraints on Llama series models.

arXiv:2504.19720cs.CL공식 코드 · Papers with Code

Taming the Titans: A Survey of Efficient LLM Inference Serving

대규모 언어 모델(LLM)의 추론 서비스는 방대한 파라미터 수와 주의(attention) 메커니즘의 높은 연산 요구로 인해 낮은 지연 시간과 높은 처리량 달성에 어려움이 있습니다. 본 논문은 인스턴스 수준의 모델 배치, 요청 스케줄링, 디코딩 길이 예측 등 기본 기법부터 GPU 클러스터 배치, 다중 인스턴스 부하 분산, 클라우드 서비스 솔루션 등 클러스터 수준 전략까지 폭넓게 다룹니다. 또한 특정 작업 및 모듈 중심의 신흥 시나리오와 기타 중요하지만 상대적으로 덜 주목받는 분야도 함께 검토합니다. 마지막으로 LLM 추론 서비스의 발전을 위한 향후 연구 방향을 제시합니다.

arXiv:2505.01712

World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular Networks

Traditional reinforcement learning (RL)-based learning approaches for wireless networks rely on expensive trial-and-error mechanisms and real-time feedback based on extensive environment interactions, which leads to low data efficiency and short-sighted policies. These limitations become particularly problematic in complex, dynamic networks with high uncertainty and long-term planning requirements. To address these limitations, in this paper, a novel world model-based learning framework is proposed to minimize packet-completeness-aware age of information (CAoI) in a vehicular network. Particularly, a challenging representative scenario is considered pertaining to a millimeter-wave (mmWave) vehicle-to-everything (V2X) communication network, which is characterized by high mobility, frequent signal blockages, and extremely short coherence time. Then, a world model framework is proposed to jointly learn a dynamic model of the mmWave V2X environment and use it to imagine trajectories for learning how to perform link scheduling. In particular, the long-term policy is learned in differentiable imagined trajectories instead of environment interactions. Moreover, owing to its imagination abilities, the world model can jointly predict time-varying wireless data and optimize link scheduling in real-world wireless and V2X networks. Thus, during intervals without actual observations, the world model remains capable of making efficient decisions. Extensive experiments are performed on a realistic simulator based on Sionna that integrates physics-based end-to-end channel modeling, ray-tracing, and scene geometries with material properties. Simulation results show that the proposed world model achieves a significant improvement in data efficiency, and achieves 26% improvement and 16% improvement in CAoI, respectively, compared to the model-based RL (MBRL) method and the model-free RL (MFRL) method.

arXiv:2504.17609공식 코드 · Papers with Code

STCL:Curriculum learning Strategies for deep learning image steganography models

Aiming at the problems of poor quality of steganographic images and slow network convergence of image steganography models based on deep learning, this paper proposes a Steganography Curriculum Learning training strategy (STCL) for deep learning image steganography models. So that only easy images are selected for training when the model has poor fitting ability at the initial stage, and gradually expand to more difficult images, the strategy includes a difficulty evaluation strategy based on the teacher model and an knee point-based training scheduling strategy. Firstly, multiple teacher models are trained, and the consistency of the quality of steganographic images under multiple teacher models is used as the difficulty score to construct the training subsets from easy to difficult. Secondly, a training control strategy based on knee points is proposed to reduce the possibility of overfitting on small training sets and accelerate the training process. Experimental results on three large public datasets, ALASKA2, VOC2012 and ImageNet, show that the proposed image steganography scheme is able to improve the model performance under multiple algorithmic frameworks, which not only has a high PSNR, SSIM score, and decoding accuracy, but also the steganographic images generated by the model under the training of the STCL strategy have a low steganography analysis scores. You can find our code at \href{https://github.com/chaos-boops/STCL}{https://github.com/chaos-boops/STCL}.

arXiv:2505.02485

Integrating Column Generation and Large Neighborhood Search for Bus Driver Scheduling with Complex Break Constraints

The Bus Driver Scheduling Problem (BDSP) is a combinatorial optimization problem with the goal to design shifts to cover prearranged bus tours. The objective takes into account the operational cost as well as the satisfaction of drivers. This problem is heavily constrained due to strict legal rules and collective agreements. The objective of this article is to provide state-of-the-art exact and hybrid solution methods that can provide high-quality solutions for instances of different sizes. This work presents a comprehensive study of both an exact method, Branch and Price (B&P), as well as a Large Neighborhood Search (LNS) framework which uses B&P or Column Generation (CG) for the repair phase to solve the BDSP. It further proposes and evaluates a novel deeper integration of B&P and LNS, storing the generated columns from the LNS subproblems and reusing them for other subproblems, or to find better global solutions. The article presents a detailed analysis of several components of the solution methods and their impact, including general improvements for the B&P subproblem, which is a high-dimensional Resource Constrained Shortest Path Problem (RCSPP), and the components of the LNS. The evaluation shows that our approach provides new state-of-the-art results for instances of all sizes, including exact solutions for small instances, and low gaps to a known lower bound for mid-sized instances. Conclusions: We observe that B&P provides the best results for small instances, while the tight integration of LNS and CG can provide high-quality solutions for larger instances, further improving over LNS which just uses CG as a black box. The proposed methods are general and can also be applied to other rule sets and related optimization problems

arXiv:2505.02483

Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning

Enabling a high-degree-of-freedom robot to learn specific skills is a challenging task due to the complexity of robotic dynamics. Reinforcement learning (RL) has emerged as a promising solution; however, addressing such problems requires the design of multiple reward functions to account for various constraints in robotic motion. Existing approaches typically sum all reward components indiscriminately to optimize the RL value function and policy. We argue that this uniform inclusion of all reward components in policy optimization is inefficient and limits the robot's learning performance. To address this, we propose an Automated Hybrid Reward Scheduling (AHRS) framework based on Large Language Models (LLMs). This paradigm dynamically adjusts the learning intensity of each reward component throughout the policy optimization process, enabling robots to acquire skills in a gradual and structured manner. Specifically, we design a multi-branch value network, where each branch corresponds to a distinct reward component. During policy optimization, each branch is assigned a weight that reflects its importance, and these weights are automatically computed based on rules designed by LLMs. The LLM generates a rule set in advance, derived from the task description, and during training, it selects a weight calculation rule from the library based on language prompts that evaluate the performance of each branch. Experimental results demonstrate that the AHRS method achieves an average 6.48% performance improvement across multiple high-degree-of-freedom robotic tasks.

arXiv:2504.17455

An approach based on metaheuristic algorithms to the timetabling problem in deregulated railway markets

The train timetabling problem in liberalized railway markets represents a challenge to the coordination between infrastructure managers and railway undertakings. Efficient scheduling is critical in maximizing infrastructure capacity and utilization while adhering as closely as possible to the requests of railway undertakings. These objectives ultimately contribute to maximizing the infrastructure manager's revenues. This paper sets out a modular simulation framework to reproduce the dynamics of deregulated railway systems. Ten metaheuristic algorithms using the MEALPY Python library are then evaluated in order to optimize train schedules in the liberalized Spanish railway market. The results show that the Genetic Algorithm outperforms others in revenue optimization, convergence speed, and schedule adherence. Alternatives, such as Particle Swarm Optimization and Ant Colony Optimization Continuous, show slower convergence and higher variability. The results emphasize the trade-off between scheduling more trains and adhering to requested times, providing insights into solving complex scheduling problems in deregulated railway systems.

arXiv:2504.05356

DyTTP: Trajectory Prediction with Normalization-Free Transformers

Accurate trajectory prediction is a cornerstone for the safe operation of autonomous driving systems, where understanding the dynamic behavior of surrounding agents is crucial. Transformer-based architectures have demonstrated significant promise in capturing complex spatio-temporality dependencies. However, their reliance on normalization layers can lead to computation overhead and training instabilities. In this work, we present a two-fold approach to address these challenges. First, we integrate DynamicTanh (DyT), which is the latest method to promote transformers, into the backbone, replacing traditional layer normalization. This modification simplifies the network architecture and improves the stability of the inference. We are the first work to deploy the DyT to the trajectory prediction task. Complementing this, we employ a snapshot ensemble strategy to further boost trajectory prediction performance. Using cyclical learning rate scheduling, multiple model snapshots are captured during a single training run. These snapshots are then aggregated via simple averaging at inference time, allowing the model to benefit from diverse hypotheses without incurring substantial additional computational cost. Extensive experiments on Argoverse datasets demonstrate that our combined approach significantly improves prediction accuracy, inference speed and robustness in diverse driving scenarios. This work underscores the potential of normalization-free transformer designs augmented with lightweight ensemble techniques in advancing trajectory forecasting for autonomous vehicles.

arXiv:2505.02861

Neural Orchestration for Multi-Agent Systems: A Deep Learning Framework for Optimal Agent Selection in Multi-Domain Task Environments

Multi-agent systems (MAS) are foundational in simulating complex real-world scenarios involving autonomous, interacting entities. However, traditional MAS architectures often suffer from rigid coordination mechanisms and difficulty adapting to dynamic tasks. We propose MetaOrch, a neural orchestration framework for optimal agent selection in multi-domain task environments. Our system implements a supervised learning approach that models task context, agent histories, and expected response quality to select the most appropriate agent for each task. A novel fuzzy evaluation module scores agent responses along completeness, relevance, and confidence dimensions, generating soft supervision labels for training the orchestrator. Unlike previous methods that hard-code agent-task mappings, MetaOrch dynamically predicts the most suitable agent while estimating selection confidence. Experiments in simulated environments with heterogeneous agents demonstrate that our approach achieves 86.3% selection accuracy, significantly outperforming baseline strategies including random selection and round-robin scheduling. The modular architecture emphasizes extensibility, allowing agents to be registered, updated, and queried independently. Results suggest that neural orchestration offers a powerful approach to enhancing the autonomy, interpretability, and adaptability of multi-agent systems across diverse task domains.

arXiv:2504.19142공식 코드 · Papers with Code

BQSched: A Non-intrusive Scheduler for Batch Concurrent Queries via Reinforcement Learning

Most large enterprises build predefined data pipelines and execute them periodically to process operational data using SQL queries for various tasks. A key issue in minimizing the overall makespan of these pipelines is the efficient scheduling of concurrent queries within the pipelines. Existing tools mainly rely on simple heuristic rules due to the difficulty of expressing the complex features and mutual influences of queries. The latest reinforcement learning (RL) based methods have the potential to capture these patterns from feedback, but it is non-trivial to apply them directly due to the large scheduling space, high sampling cost, and poor sample utilization. Motivated by these challenges, we propose BQSched, a non-intrusive Scheduler for Batch concurrent Queries via reinforcement learning. Specifically, BQSched designs an attention-based state representation to capture the complex query patterns, and proposes IQ-PPO, an auxiliary task-enhanced proximal policy optimization (PPO) algorithm, to fully exploit the rich signals of Individual Query completion in logs. Based on the RL framework above, BQSched further introduces three optimization strategies, including adaptive masking to prune the action space, scheduling gain-based query clustering to deal with large query sets, and an incremental simulator to reduce sampling cost. To our knowledge, BQSched is the first non-intrusive batch query scheduler via RL. Extensive experiments show that BQSched can significantly improve the efficiency and stability of batch query scheduling, while also achieving remarkable scalability and adaptability in both data and queries. For example, across all DBMSs and scales tested, BQSched reduces the overall makespan of batch queries on TPC-DS benchmark by an average of 34% and 13%, compared with the commonly used heuristic strategy and the adapted RL-based scheduler, respectively.

arXiv:3704.79364

LUNDRY MANAGEMENT SYSTEM PROJECT REPORT

Laundry firms currently use a manual system for the management and maintenance of critical information. The current system requires numerous paper forms, with data stores spread throughout the laundry management infrastructure. Often information is incomplete or does not follow management standards. Records are often lost in transit during computation requiring a comprehensive auditing process to ensure that no vital information is lost. Multiple copies of the same information exist in the laundry firm data and may lead to inconsistencies in data in various data stores. A significant part of the operation of any laundry firm involves the acquisition, management and timely retrieval of great volumes of information. This information typically involves; customer personal information and clothing records history, user information, price of delivery and received date, users scheduling as regards customers details and dealings in service rendered, also our products package waiting list. All of this information must be managed in an efficient and cost wise fashion so that the organization resources may be effectively utilized. We present the design and implementation of a laundry database management system (LBMS) used in a laundry establishment. Laundry firms are usually faced with difficulties in keeping detailed records of customers clothing; this little problem as seen to most laundry firms is highly discouraging as customers are filled with disappointments, arising from issues such as customer clothes mix-ups and untimely retrieval of clothes. The aim of this application is to determine the number of clothes collected, in relation to their owners, as this also helps the users fix a date for the collection of their clothes. Also customer’s information is secured, as a specific id is allocated per registration to avoid contrasting information.

arXiv:2504.14425

Optimal Scheduling of Dynamic Transport

Flow-based methods for sampling and generative modeling use continuous-time dynamical systems to represent a {transport map} that pushes forward a source measure to a target measure. The introduction of a time axis provides considerable design freedom, and a central question is how to exploit this freedom. Though many popular methods seek straight line (i.e., zero acceleration) trajectories, we show here that a specific class of ``curved'' trajectories can significantly improve approximation and learning. In particular, we consider the unit-time interpolation of any given transport map $T$ and seek the schedule $\tau: [0,1] \to [0,1]$ that minimizes the spatial Lipschitz constant of the corresponding velocity field over all times $t \in [0,1]$. This quantity is crucial as it allows for control of the approximation error when the velocity field is learned from data. We show that, for a broad class of source/target measures and transport maps $T$, the \emph{optimal schedule} can be computed in closed form, and that the resulting optimal Lipschitz constant is \emph{exponentially smaller} than that induced by an identity schedule (corresponding to, for instance, the Wasserstein geodesic). Our proof technique relies on the calculus of variations and $\Gamma$-convergence, allowing us to approximate the aforementioned degenerate objective by a family of smooth, tractable problems.

arXiv:2504.14556

LLM-Enabled In-Context Learning for Data Collection Scheduling in UAV-assisted Sensor Networks

Unmanned Aerial Vehicles (UAVs) are increasingly being used in various private and commercial applications, e.g. traffic control, package delivery, and Search and Rescue (SAR) operations. Machine Learning (ML) methods used in UAV-assisted Sensor Networks (UASNETs) and especially in Deep Reinforcement Learning (DRL) face challenges such as complex and lengthy model training, gaps between simulation and reality, and low sample efficiency, which conflict with the urgency of emergencies such as SAR operations. This paper proposes In-Context Learning (ICL)-based Data Collection Scheduling (ICLDC) scheme, as an alternative to DRL in emergencies. The UAV collects and transmits logged sensory data, to an LLM, to generate a task description in natural language, from which it obtains a data collection schedule to be executed by the UAV. The system continuously adapts by adding feedback to task descriptions and utilizing feedback for future decisions. This method is tested against jailbreaking attacks, where task description is manipulated to undermine network performance, highlighting the vulnerability of LLMs to such attacks. The proposed ICLDC outperforms the Maximum Channel Gain by reducing cumulative packet loss by approximately 56\%. ICLDC presents a promising direction for intelligent scheduling and control in UAV-assisted data collection.