It is envisioned that the next generations of wireless communication environment will be characterized with dense traffic demand due to the prediction that there will be large numbers of active users. Hence, it is important to find a solution to deal with such dense numbers of users. This paper investigates optimizing the connectivity and users scheduling to improve the performance of near and far field users in a downlink, multiuser, massive MIMO-NOMA system. For the considered system model, combining NOMA side by side with massive MIMO offers a great opportunity to exploit the available radio resources and boost the overall system efficiency. The paper proposes separate clustering of near field users and far field users. It also proposes using a beamforming scheme to separately serve the users within each cluster. However, NOMA is proposed to be applied among all users to boost resource sharing. In particular, a cognitive-NOMA beamforming scheme and NOMA themed beamforming are proposed to serve the users within each cluster, and they are compared against random beamforming from literature. Simulation results show that both of the proposed beamforming schemes proved their superiority as compared to random beamforming. Several scheduling techniques were also considered in this paper to examine possible solutions for boosting the system performance considered, namely, priority, joint, dynamic, and fairness-based scheduling techniques for both near field and far field users. The paper also proposes a suboptimal, fairness aiming and gradual allocation approach for allocating the transmission power among the users. The results show that user-clustering offers better connectivity and scheduling performance than the case where no clustering is applied.
In recent years, Large Language Models (LLM) such as ChatGPT, CoPilot, and Gemini have been widely adopted in different areas. As the use of LLMs continues to grow, many efforts have focused on reducing the massive training overheads of these models. But it is the environmental impact of handling user requests to LLMs that is increasingly becoming a concern. Recent studies estimate that the costs of operating LLMs in their inference phase can exceed training costs by 25x per year. As LLMs are queried incessantly, the cumulative carbon footprint for the operational phase has been shown to far exceed the footprint during the training phase. Further, estimates indicate that 500 ml of fresh water is expended for every 20-50 requests to LLMs during inference. To address these important sustainability issues with LLMs, we propose a novel framework called SLIT to co-optimize LLM quality of service (time-to-first token), carbon emissions, water usage, and energy costs. The framework utilizes a machine learning (ML) based metaheuristic to enhance the sustainability of LLM hosting across geo-distributed cloud datacenters. Such a framework will become increasingly vital as LLMs proliferate.
This paper characterizes the impacts of channel estimation errors and Rician factors on achievable data rate and investigates the user scheduling strategy, combining scheme, power control, and dynamic bandwidth allocation to maximize the sum data rate in the distributed multiple-input-multiple-output (MIMO)-enabled low earth orbit (LEO) satellite networks. However, due to the resource-assignment problem, it is challenging to find the optimal solution for maximizing the sum data rate. To transform this problem into a more tractable form, we first quantify the channel estimation errors based on the minimum mean square error (MMSE) estimator and rigorously derive a closed-form lower bound of the achievable data rate, offering an explicit formulation for resource allocation. Then, to solve the NP-hard problem, we decompose it into three sub-problems, namely, user scheduling strategy, joint combination and power control, and dynamic bandwidth allocation, by using alternative optimization (AO). Specifically, the user scheduling is formulated as a graph coloring problem by iteratively updating an undirected graph based on user requirements, which is then solved using the DSatur algorithm. For the combining weights and power control, the successive convex approximation (SCA) and geometrical programming (GP) are adopted to obtain the sub-optimal solution with lower complexity. Finally, the optimal bandwidth allocation can be achieved by solving the concave problem. Numerical results validate the analytical tightness of the derived bound, especially for large Rician factors, and demonstrate significant performance gains over other benchmarks.
Decision Transformer (DT) has recently demonstrated strong generalizability in dynamic resource allocation within unmanned aerial vehicle (UAV) networks, compared to conventional deep reinforcement learning (DRL). However, its performance is hindered due to zero-padding for varying state dimensions, inability to manage long-term energy constraint, and challenges in acquiring expert samples for few-shot fine-tuning in new scenarios. To overcome these limitations, we propose an attention-enhanced prompt Decision Transformer (APDT) framework to optimize trajectory planning and user scheduling, aiming to minimize the average age of information (AoI) under long-term energy constraint in UAV-assisted Internet of Things (IoT) networks. Specifically, we enhance the convenional DT framework by incorporating an attention mechanism to accommodate varying numbers of terrestrial users, introducing a prompt mechanism based on short trajectory demonstrations for rapid adaptation to new scenarios, and designing a token-assisted method to address the UAV's long-term energy constraint. The APDT framework is first pre-trained on offline datasets and then efficiently generalized to new scenarios. Simulations demonstrate that APDT achieves twice faster in terms of convergence rate and reduces average AoI by $8\%$ compared to conventional DT.
소셜 미디어 콘텐츠 모더레이션처럼 작업의 지연 비용이 콘텐츠의 노출 경로(view trajectory)에 따라 달라지고, 그 경로가 사전에 알려져 있지 않으며 시간에 따라 변화하는 상황은 전통적인 큐잉 스케줄링의 가정과 크게 다릅니다. 이러한 현실을 반영하여, 논문은 각 작업의 상태가 마코프 체인(Markov chain)으로 진화하고 상태별 순간 보유 비용이 달라지는 큐잉 모델을 설정함으로써, 불확실하면서도 점진적으로 드러나는 비용 구조를 정면으로 다룹니다. 이 과정에서 널리 쓰이던 즉시 비용 기반 cμ-rule(cost-times-service-rate rule)과 기대 잔여 비용 기반 cμ/θ-rule(cost-times-service-rate over decay-rate rule)이 모두 최적이 될 수 없음을 보이며, 단순한 현재 비용이나 남은 기대 비용만으로는 미래의 서비스 기회를 충분히 반영할 수 없다는 점을 핵심 문제로 제시합니다. 이를 해결하기 위해 저자들은 각 작업을 Markovian ski-rental 문제로 해석하고, 불확실성이 부분적으로 해소될 때 생기는 기회비용을 조정하는 인덱스형 정책 Opportunity-adjusted Remaining Cost(OaRC)를 제안합니다. OaRC의 핵심은 지금 당장 처리할지, 아니면 더 유리한 미래의 서비스를 기다릴지에 대한 판단을 현재 상태의 비용뿐 아니라 남아 있는 기회까지 포함해 정교하게 조정한다는 데 있습니다.
방법론적으로는 임의의 상태 기반 우선순위 정책 Prio(o)를 유체 해(fluid solution)로 대응시키고, 이를 바탕으로 시스템의 장기 거동을 정적 최적화 문제로 변환하는 분석 틀을 구축합니다. 특히 우선순위 순서에 따라 서비스가 어떻게 배분되는지를 water-filling 구조로 정식화하고, 상태 공간을 Top/Sub 분해로 나누어 완전 서비스 상태, 부분 서비스 상태, 차단 상태를 체계적으로 구분합니다. 이러한 구성은 상태 간 전이 효과가 단순한 독립 항들의 합이 아니라 조상-자식 관계를 따라 연쇄적으로 전파된다는 점을 명확히 드러내며, 유체 수준에서 OaRC가 왜 자연스러운 해인지 설명해 줍니다. 더 나아가 이 유체 해가 OriginalFluid의 feasible solution일 뿐 아니라 전용량을 사용하는 해로 정리되므로, OaRC는 직관적인 휴리스틱이 아니라 최적화 관점에서 정당화되는 정책으로 자리매김합니다.
이 논문의 중요한 기여는 성능 보장에서도 뚜렷합니다. 저자들은 OaRC의 최적성 격차가 \tilde{O}(\sqrt{N})로 제어됨을 보이고, 이를 통해 시스템 크기 N이 커지는 과부하 체제에서 점근적 최적성(asymptotic optimality)을 달성함을 입증합니다. 특히 이 보장은 상태공간의 크기에 의존하지 않기 때문에, 문맥 정보가 풍부한 작업 상태를 다루는 실제 환경에서도 확장성이 뛰어납니다. 마지막으로 온라인 광고와 사용자 생성 콘텐츠라는 두 가지 보유 비용 패턴에 대한 합성 및 실데이터 시뮬레이션은, OaRC가 기존의 두 기준 정책보다 일관되게 우수하다는 점을 보여 주며 이론적 결과의 실용적 타당성을 뒷받침합니다. 결과적으로 이 연구는 불확실하고 진화하는 비용 구조를 가진 큐잉 시스템에서, 현재 비용과 미래 기회 사이의 균형을 새로운 방식으로 정식화한 스케줄링 원리를 제시한다는 점에서 의미가 큽니다.
Generative image editing using diffusion models has become a prevalent application in today's AI cloud services. In production environments, image editing typically involves a mask that specifies the regions of an image template to be edited. The use of masks provides direct control over the editing process and introduces sparsity in the model inference. In this paper, we present InstGenIE, a system that efficiently serves image editing requests. The key insight behind InstGenIE is that image editing only modifies the masked regions of image templates while preserving the original content in the unmasked areas. Driven by this insight, InstGenIE judiciously skips redundant computations associated with the unmasked areas by reusing cached intermediate activations from previous inferences. To mitigate the high cache loading overhead, InstGenIE employs a bubble-free pipeline scheme that overlaps computation with cache loading. Additionally, to reduce queuing latency in online serving while improving the GPU utilization, InstGenIE proposes a novel continuous batching strategy for diffusion model serving, allowing newly arrived requests to join the running batch in just one step of denoising computation, without waiting for the entire batch to complete. As heterogeneous masks induce imbalanced loads, InstGenIE also develops a load balancing strategy that takes into account the loads of both computation and cache loading. Collectively, InstGenIE outperforms state-of-the-art diffusion serving systems for image editing, achieving up to 3x higher throughput and reducing average request latency by up to 14.7x while ensuring image quality.
Speculative decoding accelerates Large Language Model (LLM) inference by employing a small speculative model (SSM) to generate multiple candidate tokens and verify them using the LLM in parallel. This technique has been widely integrated into LLM inference serving systems. However, inference requests typically exhibit uncertain execution time, which poses a significant challenge of efficiently scheduling requests in these systems. Existing work estimates execution time based solely on predicted output length, which could be inaccurate because execution time depends on both output length and token acceptance rate of verification by the LLM. In this paper, we propose a semi-clairvoyant request scheduling algorithm called Least-Attained/Perceived-Service for Speculative Decoding (LAPS-SD). Given a number of inference requests, LAPS-SD can effectively minimize average inference latency by adaptively scheduling requests according to their features during decoding. When the token acceptance rate is dynamic and execution time is difficult to estimate, LAPS-SD maintains multiple priority queues and allows request execution preemption across different queues. Once the token acceptance rate becomes stable, LAPS-SD can accurately estimate the execution time and schedule requests accordingly. Extensive experiments show that LAPS-SD reduces inference latency by approximately 39\% compared to state-of-the-art scheduling methods.
Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted inference framework that splits LLM workloads between edge and server GPUs using a speculative decoding scheme, exchanging only token outputs over the network. SpecEdge employs proactive edge drafting to overlap edge token creation with server verification and pipeline-aware scheduling that interleaves multiple user requests to increase server-side throughput. Experiments show SpecEdge enhances overall cost efficiency by 1.91x through achieving 2.22x server throughput, and reduces inter token latency by 11.24% compared to a server-only baseline, introducing a scalable, cost-effective paradigm for LLM serving.
Guidance is a cornerstone of modern diffusion models, playing a pivotal role in conditional generation and enhancing the quality of unconditional samples. However, current approaches to guidance scheduling--determining the appropriate guidance weight--are largely heuristic and lack a solid theoretical foundation. This work addresses these limitations on two fronts. First, we provide a theoretical formalization that precisely characterizes the relationship between guidance strength and classifier confidence. Second, building on this insight, we introduce a stochastic optimal control framework that casts guidance scheduling as an adaptive optimization problem. In this formulation, guidance strength is not fixed but dynamically selected based on time, the current sample, and the conditioning class, either independently or in combination. By solving the resulting control problem, we establish a principled foundation for more effective guidance in diffusion models.
Long-context supervised fine-tuning (Long-SFT) plays a vital role in enhancing the performance of large language models (LLMs) on long-context tasks. To smoothly adapt LLMs to long-context scenarios, this process typically entails training on mixed datasets containing both long and short sequences. However, this heterogeneous sequence length distribution poses significant challenges for existing training systems, as they fail to simultaneously achieve high training efficiency for both long and short sequences, resulting in sub-optimal end-to-end system performance in Long-SFT. In this paper, we present a novel perspective on data scheduling to address the challenges posed by the heterogeneous data distributions in Long-SFT. We propose Skrull, a dynamic data scheduler specifically designed for efficient long-SFT. Through dynamic data scheduling, Skrull balances the computation requirements of long and short sequences, improving overall training efficiency. Furthermore, we formulate the scheduling process as a joint optimization problem and thoroughly analyze the trade-offs involved. Based on those analysis, Skrull employs a lightweight scheduling algorithm to achieve near-zero cost online scheduling in Long-SFT. Finally, we implement Skrull upon DeepSpeed, a state-of-the-art distributed training system for LLMs. Experimental results demonstrate that Skrull outperforms DeepSpeed by 3.76x on average (up to 7.54x) in real-world long-SFT scenarios.
Reinforcement learning (RL) is increasingly applied to real-world problems involving complex and structured decisions, such as routing, scheduling, and assortment planning. These settings challenge standard RL algorithms, which struggle to scale, generalize, and exploit structure in the presence of combinatorial action spaces. We propose Structured Reinforcement Learning (SRL), a novel actor-critic framework that embeds combinatorial optimization layers into the actor neural network. We enable end-to-end learning of the actor via Fenchel-Young losses and provide a geometric interpretation of SRL as a primal-dual algorithm in the dual of the moment polytope. Across six environments with exogenous and endogenous uncertainty, SRL matches or surpasses the performance of unstructured RL and imitation learning on static tasks and improves over these baselines by up to 92% on dynamic problems, with improved stability and convergence speed.
Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of persistent memory to track evolving goals and task dependencies, undermining trust in autonomous agents. We introduce the Task Memory Engine (TME), a modular memory controller that transforms existing LLMs into robust, revision-aware agents without fine-tuning. TME implements a spatial memory framework that replaces flat context with graph-based structures to support consistent, multi-turn reasoning. Departing from linear concatenation and ReAct-style prompting, TME builds a dynamic task graph -- either a tree or directed acyclic graph (DAG) -- to map user inputs to subtasks, align them with prior context, and enable dependency-tracked revisions. Its Task Representation and Intent Management (TRIM) component models task semantics and user intent to ensure accurate interpretation. Across four multi-turn scenarios-trip planning, cooking, meeting scheduling, and shopping cart editing -- TME eliminates 100% of hallucinations and misinterpretations in three tasks, and reduces hallucinations by 66.7% and misinterpretations by 83.3% across 27 user turns, outperforming ReAct. TME's modular design supports plug-and-play deployment and domain-specific customization, adaptable to both personal assistants and enterprise automation. We release TME's codebase, benchmarks, and components as open-source resources, enabling researchers to develop reliable LLM agents. TME's scalable architecture addresses a critical gap in agent performance across complex, interactive settings.
The electrification of transportation and the increased adoption of decentralized renewable energy generation have added complexity to managing Renewable Energy Communities (RECs). Integrating Electric Vehicle (EV) charging with building energy systems like heating, ventilation, air conditioning (HVAC), photovoltaic (PV) generation, and battery storage presents significant opportunities but also practical challenges. Reinforcement learning (RL), particularly MultiAgent Deep Deterministic Policy Gradient (MADDPG) algorithms, have shown promising results in simulation, outperforming heuristic control strategies. However, translating these successes into real-world deployments faces substantial challenges, including incomplete and noisy data, integration of heterogeneous subsystems, synchronization issues, unpredictable occupant behavior, and missing critical EV state-of-charge (SoC) information. This paper introduces a framework designed explicitly to handle these complexities and bridge the simulation to-reality gap. The framework incorporates EnergAIze, a MADDPG-based multi-agent control strategy, and specifically addresses challenges related to real-world data collection, system integration, and user behavior modeling. Preliminary results collected from a real-world operational REC with four residential buildings demonstrate the practical feasibility of our approach, achieving an average 9% reduction in daily peak demand and a 5% decrease in energy costs through optimized load scheduling and EV charging behaviors. These outcomes underscore the framework's effectiveness, advancing the practical deployment of intelligent energy management solutions in RECs.
Large Language Models (LLMs), due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even cause crashes, as demonstrated by denial-of-service (DoS) attacks designed for LLMs. However, existing works lack mitigation strategies against such threats, resulting in unresolved security risks for real-world LLM deployments. To this end, we propose the Pluggable and Dynamic DoS-Defense Framework ($PD^3F$), which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides. On the input side, we propose the Resource Index to guide Dynamic Request Polling Scheduling, thereby reducing resource usage induced by malicious attacks under high-concurrency scenarios. On the output side, we introduce the Adaptive End-Based Suppression mechanism, which terminates excessive malicious generation early. Experiments across six models demonstrate that $PD^3F$ significantly mitigates resource consumption attacks, improving users' access capacity by up to 500% during adversarial load. $PD^3F$ represents a step toward the resilient and resource-aware deployment of LLMs against resource consumption attacks.
Spatio-temporal prediction is a pivotal task with broad applications in traffic management, climate monitoring, energy scheduling, etc. However, existing methodologies often struggle to balance model expressiveness and computational efficiency, especially when scaling to large real-world datasets. To tackle these challenges, we propose STH-SepNet (Spatio-Temporal Hypergraph Separation Networks), a novel framework that decouples temporal and spatial modeling to enhance both efficiency and precision. Therein, the temporal dimension is modeled using lightweight large language models, which effectively capture low-rank temporal dynamics. Concurrently, the spatial dimension is addressed through an adaptive hypergraph neural network, which dynamically constructs hyperedges to model intricate, higher-order interactions. A carefully designed gating mechanism is integrated to seamlessly fuse temporal and spatial representations. By leveraging the fundamental principles of low-rank temporal dynamics and spatial interactions, STH-SepNet offers a pragmatic and scalable solution for spatio-temporal prediction in real-world applications. Extensive experiments on large-scale real-world datasets across multiple benchmarks demonstrate the effectiveness of STH-SepNet in boosting predictive performance while maintaining computational efficiency. This work may provide a promising lightweight framework for spatio-temporal prediction, aiming to reduce computational demands and while enhancing predictive performance. Our code is avaliable at https://github.com/SEU-WENJIA/ST-SepNet-Lightweight-LLMs-Meet-Adaptive-Hypergraphs.
Efficiently managing compute resources for Large Language Model (LLM) inference remains challenging due to the inherently stochastic and variable lengths of autoregressive text generation. Accurately estimating response lengths in advance enables proactive resource allocation, yet existing approaches either bias text generation towards certain lengths or rely on assumptions that ignore model- and prompt-specific variability. We introduce CASTILLO, a dataset characterizing response length distributions across 13 widely-used open-source LLMs evaluated on seven distinct instruction-following corpora. For each $\langle$prompt, model$\rangle$ sample pair, we generate 10 independent completions using fixed decoding hyper-parameters, record the token length of each response, and publish summary statistics (mean, std-dev, percentiles), along with the shortest and longest completions, and the exact generation settings. Our analysis reveals significant inter- and intra-model variability in response lengths (even under identical generation settings), as well as model-specific behaviors and occurrences of partial text degeneration in only subsets of responses. CASTILLO enables the development of predictive models for proactive scheduling and provides a systematic framework for analyzing model-specific generation behaviors. We publicly release the dataset and code to foster research at the intersection of generative language modeling and systems.
The problems that tobacco workshops encounter include poor curing, inconsistencies in supplies, irregular scheduling, and a lack of oversight, all of which drive up expenses and worse quality. Large quantities make manual examination costly, sluggish, and unreliable. Deep convolutional neural networks have recently made strides in capabilities that transcend those of conventional methods. To effectively enhance them, nevertheless, extensive customization is needed to account for subtle variations in tobacco grade. This study introduces InspectionV3, an integrated solution for automated flue-cured tobacco grading that makes use of a customized deep convolutional neural network architecture. A scope that covers color, maturity, and curing subtleties is established via a labelled dataset consisting of 21,113 images spanning 20 quality classes. Expert annotators performed preprocessing on the tobacco leaf images, including cleaning, labelling, and augmentation. Multi-layer CNN factors use batch normalization to describe domain properties like as permeability and moisture spots, and so account for the subtleties of the workshop. Its expertise lies in converting visual patterns into useful information for enhancing workflow. Fast notifications are made possible by real-time, on-the-spot grading that matches human expertise. Images-powered analytics dashboards facilitate the tracking of yield projections, inventories, bottlenecks, and the optimization of data-driven choices. More labelled images are assimilated after further retraining, improving representational capacities and enabling adaptations for seasonal variability. Metrics demonstrate 97% accuracy, 95% precision and recall, 96% F1-score and AUC, 95% specificity; validating real-world viability.
Masked diffusion models (MDMs) have achieved notable progress in modeling discrete data, while their potential in molecular generation remains underexplored. In this work, we explore their potential and introduce the surprising result that naively applying standards MDMs severely degrades the performance. We identify the critical cause of this issue as a state-clashing problem-where the forward diffusion of distinct molecules collapse into a common state, resulting in a mixture of reconstruction targets that cannot be learned using typical reverse diffusion process with unimodal predictions. To mitigate this, we propose Masked Element-wise Learnable Diffusion (MELD) that orchestrates per-element corruption trajectories to avoid collision between distinct molecular graphs. This is achieved through a parameterized noise scheduling network that assigns distinct corruption rates to individual graph elements, i.e., atoms and bonds. Extensive experiments on diverse molecular benchmarks reveal that MELD markedly enhances overall generation quality compared to element-agnostic noise scheduling, increasing the chemical validity of vanilla MDMs on ZINC250K from 15% to 93%, Furthermore, it achieves state-of-the-art property alignment in conditional generation tasks.
This paper addresses the limitations of multi-node perception and delayed scheduling response in distributed systems by proposing a GNN-based multi-node collaborative perception mechanism. The system is modeled as a graph structure. Message-passing and state-update modules are introduced. A multi-layer graph neural network is constructed to enable efficient information aggregation and dynamic state inference among nodes. In addition, a perception representation method is designed by fusing local states with global features. This improves each node's ability to perceive the overall system status. The proposed method is evaluated within a customized experimental framework. A dataset featuring heterogeneous task loads and dynamic communication topologies is used. Performance is measured in terms of task completion rate, average latency, load balancing, and transmission efficiency. Experimental results show that the proposed method outperforms mainstream algorithms under various conditions, including limited bandwidth and dynamic structural changes. It demonstrates superior perception capabilities and cooperative scheduling performance. The model achieves rapid convergence and efficient responses to complex system states.
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, where models generate verbose and tangential reasoning traces even for simple queries. Recent works have tried to mitigate this by enforcing fixed token budgets, however, this can lead to underthinking, especially on harder problems. Through empirical analysis, we identify that this inefficiency often stems from unclear problem-solving strategies. To formalize this, we develop a theoretical model, BBAM (Bayesian Budget Allocation Model), which models reasoning as a sequence of sub-questions with varying uncertainty, and introduce the $E^3$ metric to capture the trade-off between correctness and computation efficiency. Building on theoretical results from BBAM, we propose Plan-and-Budget, a model-agnostic, test-time framework that decomposes complex queries into sub-questions and allocates token budgets based on estimated complexity using adaptive scheduling. Plan-and-Budget improves reasoning efficiency across a range of tasks and models, achieving up to +70% accuracy gains, -39% token reduction, and +187.5% improvement in $E^3$. Notably, it elevates a smaller model (DS-Qwen-32B) to match the efficiency of a larger model (DS-LLaMA-70B)-demonstrating Plan-and-Budget's ability to close performance gaps without retraining. Our code is available at anonymous.4open.science/r/P-and-B-6513/.