Coordinated Beamforming for RIS-Empowered ISAC Systems over Secure Low-Altitude Networks

Emerging as a cornerstone for next-generation wireless networks, integrated sensing and communication (ISAC) systems demand innovative solutions to balance spectral efficiency and sensing accuracy. In this paper, we propose a coordinated beamforming framework for a reconfigurable intelligent surface (RIS)-empowered ISAC system, where the active precoding at the dual-functional base station (DFBS) and the passive beamforming at the RIS are jointly optimized to provide communication services for legitimate unmanned aerial vehicles (UAVs) while sensing the unauthorized UAVs. The sum-rate of all legitimate UAVs are maximized, while satisfying the radar sensing signal-to-noise ratio requirements, the transmit power constraints, and the reflection coefficients of the RIS. To address the inherent non-convexity from coupled variables, we propose a low-complexity algorithm integrating fractional programming with alternating optimization, featuring convergence guarantees. Numerical results demonstrate that the proposed algorithm achieves higher data rate compared to disjoint optimization benchmarks. This underscores RIS's pivotal role in harmonizing communication and target sensing functionalities for low-altitude networks.

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning

Scaling laws motivate the development of Time Series Foundation Models (TSFMs) that pre-train vast parameters and achieve remarkable zero-shot forecasting performance. Surprisingly, even after fine-tuning, TSFMs cannot consistently outperform smaller, specialized models trained on full-shot downstream data. A key question is how to realize effective adaptation of TSFMs for a target forecasting task. Through empirical studies on various TSFMs, the pre-trained models often exhibit inherent sparsity and redundancy in computation, suggesting that TSFMs have learned to activate task-relevant network substructures to accommodate diverse forecasting tasks. To preserve this valuable prior knowledge, we propose a structured pruning method to regularize the subsequent fine-tuning process by focusing it on a more relevant and compact parameter space. Extensive experiments on seven TSFMs and six benchmarks demonstrate that fine-tuning a smaller, pruned TSFM significantly improves forecasting performance compared to fine-tuning original models. This "prune-then-finetune" paradigm often enables TSFMs to achieve state-of-the-art performance and surpass strong specialized baselines.

In-Context Adaptation to Concept Drift for Learned Database Operations

Machine learning has demonstrated transformative potential for database operations, such as query optimization and in-database data analytics. However, dynamic database environments, characterized by frequent updates and evolving data distributions, introduce concept drift, which leads to performance degradation for learned models and limits their practical applicability. Addressing this challenge requires efficient frameworks capable of adapting to shifting concepts while minimizing the overhead of retraining or fine-tuning. In this paper, we propose FLAIR, an online adaptation framework that introduces a new paradigm called \textit{in-context adaptation} for learned database operations. FLAIR leverages the inherent property of data systems, i.e., immediate availability of execution results for predictions, to enable dynamic context construction. By formalizing adaptation as $f:(\mathbf{x} \,| \,\mathcal{C}_t) \to \mathbf{y}$, with $\mathcal{C}_t$ representing a dynamic context memory, FLAIR delivers predictions aligned with the current concept, eliminating the need for runtime parameter optimization. To achieve this, FLAIR integrates two key modules: a Task Featurization Module for encoding task-specific features into standardized representations, and a Dynamic Decision Engine, pre-trained via Bayesian meta-training, to adapt seamlessly using contextual information at runtime. Extensive experiments across key database tasks demonstrate that FLAIR outperforms state-of-the-art baselines, achieving up to 5.2x faster adaptation and reducing error by 22.5% for cardinality estimation.

A Framework for Elastic Adaptation of User Multiple Intents in Sequential Recommendation

Recently, substantial research has been conducted on sequential recommendation, with the objective of forecasting the subsequent item by leveraging a user's historical sequence of interacted items. Prior studies employ both capsule networks and self-attention techniques to effectively capture diverse underlying intents within a user's interaction sequence, thereby achieving the most advanced performance in sequential recommendation. However, users could potentially form novel intents from fresh interactions as the lengths of user interaction sequences grow. Consequently, models need to be continually updated or even extended to adeptly encompass these emerging user intents, referred as incremental multi-intent sequential recommendation. % We refer to this problem as incremental multi-intent sequential recommendation, which has not yet been well investigated in the existing literature. In this paper, we propose an effective Incremental learning framework for user Multi-intent Adaptation in sequential recommendation called IMA, which augments the traditional fine-tuning strategy with the existing-intents retainer, new-intents detector, and projection-based intents trimmer to adaptively expand the model to accommodate user's new intents and prevent it from forgetting user's existing intents. Furthermore, we upgrade the IMA into an Elastic Multi-intent Adaptation (EMA) framework which can elastically remove inactive intents and compress user intent vectors under memory space limit. Extensive experiments on real-world datasets verify the effectiveness of the proposed IMA and EMA on incremental multi-intent sequential recommendation, compared with various baselines.

Feature Staleness Aware Incremental Learning for CTR Prediction

Click-through Rate (CTR) prediction in real-world recommender systems often deals with billions of user interactions every day. To improve the training efficiency, it is common to update the CTR prediction model incrementally using the new incremental data and a subset of historical data. However, the feature embeddings of a CTR prediction model often get stale when the corresponding features do not appear in current incremental data. In the next period, the model would have a performance degradation on samples containing stale features, which we call the feature staleness problem. To mitigate this problem, we propose a Feature Staleness Aware Incremental Learning method for CTR prediction (FeSAIL) which adaptively replays samples containing stale features. We first introduce a staleness aware sampling algorithm (SAS) to sample a fixed number of stale samples with high sampling efficiency. We then introduce a staleness aware regularization mechanism (SAR) for a fine-grained control of the feature embedding updating. We instantiate FeSAIL with a general deep learning-based CTR prediction model and the experimental results demonstrate FeSAIL outperforms various state-of-the-art methods on four benchmark datasets.

Relative Contrastive Learning for Sequential Recommendation with Similarity-based Positive Pair Selection

Contrastive Learning (CL) enhances the training of sequential recommendation (SR) models through informative self-supervision signals. Existing methods often rely on data augmentation strategies to create positive samples and promote representation invariance. Some strategies such as item reordering and item substitution may inadvertently alter user intent. Supervised Contrastive Learning (SCL) based methods find an alternative to augmentation-based CL methods by selecting same-target sequences (interaction sequences with the same target item) to form positive samples. However, SCL-based methods suffer from the scarcity of same-target sequences and consequently lack enough signals for contrastive learning. In this work, we propose to use similar sequences (with different target items) as additional positive samples and introduce a Relative Contrastive Learning (RCL) framework for sequential recommendation. RCL comprises a dual-tiered positive sample selection module and a relative contrastive learning module. The former module selects same-target sequences as strong positive samples and selects similar sequences as weak positive samples. The latter module employs a weighted relative contrastive loss, ensuring that each sequence is represented closer to its strong positive samples than its weak positive samples. We apply RCL on two mainstream deep learning-based SR models, and our empirical results reveal that RCL can achieve 4.88% improvement averagely than the state-of-the-art SR methods on five public datasets and one private dataset.

Full-Duplex ISCC for Low-Altitude Networks: Resource Allocation and Coordinated Beamforming

This paper investigates an integrated sensing, communication, and computing system deployed over low-altitude networks for enabling applications within the low-altitude economy. In the considered system, a full-duplex enabled unmanned aerial vehicle (UAV) is dispatched in the airspace, functioning as a UAV-enabled low-altitude platform (ULAP). The ULAP is capable of achieving simultaneous information transmission, target sensing, and mobile edge computing services. To reduce the overall energy consumption of the system while meeting the sensing beampattern threshold and user computation requirements, we formulate an energy consumption minimization problem by jointly optimizing the task allocation, computation resource allocation, transmit beamforming, and receive beamforming. Since the problem is non-convex and involves highly coupled variables, we propose an efficient algorithm based on alternation optimization, which decomposes the original problem into tractable convex subproblems. Moreover, we analyze the convergence and complexity of the proposed algorithm. Numerical results demonstrate that the proposed scheme saves up to 54.12\% energy consumption performance compared to the benchmark schemes.

Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving

Large language model (LLM) inference serving systems are essential to various LLM-based applications. As demand for LLM services continues to grow, scaling these systems to handle high request rates while meeting latency Service-Level Objectives (SLOs), referred to as effective throughput, becomes critical. However, existing systems often struggle to improve effective throughput, primarily due to a significant decline in Time To First Token (TTFT) SLO attainment. We identify two major causes of this bottleneck: (1) memory-intensive KV cache that limits batch size expansion under GPU memory constraints, and (2) rigid batch composition enforced by the default First-Come-First-Serve scheduling policy. In this paper, we introduce Apt-Serve, a scalable framework designed to enhance effective throughput in LLM inference serving. Apt-Serve features a new hybrid cache scheme that combines KV cache with a memory-efficient hidden cache for reusable input hidden state vectors, allowing large batch sizes and improving request concurrency. Based on the hybrid cache, Apt-Serve employs an adaptive runtime scheduling mechanism that dynamically optimizes batch composition. We formally define the adaptive scheduling optimization problem and propose an efficient algorithm with theoretical guarantees. Extensive evaluations on three real-world datasets and LLMs ranging from 13B to 66B parameters demonstrate that Apt-Serve achieves up to 8.8x improvement in effective throughput compared to the state-of-the-art inference serving systems.

Retrieval-Augmented Generation for Mobile Edge Computing via Large Language Model

The rapid evolution of mobile edge computing (MEC) has introduced significant challenges in optimizing resource allocation in highly dynamic wireless communication systems, in which task offloading decisions should be made in real-time. However, existing resource allocation strategies cannot well adapt to the dynamic and heterogeneous characteristics of MEC systems, since they are short of scalability, context-awareness, and interpretability. To address these issues, this paper proposes a novel retrieval-augmented generation (RAG) method to improve the performance of MEC systems. Specifically, a latency minimization problem is first proposed to jointly optimize the data offloading ratio, transmit power allocation, and computing resource allocation. Then, an LLM-enabled information-retrieval mechanism is proposed to solve the problem efficiently. Extensive experiments across multi-user, multi-task, and highly dynamic offloading scenarios show that the proposed method consistently reduces latency compared to several DL-based approaches, achieving 57% improvement under varying user computing ability, 86% with different servers, 30% under distinct transmit powers, and 42% for varying data volumes. These results show the effectiveness of LLM-driven solutions to solve the resource allocation problems in MEC systems.

Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting

Time series forecasting always faces the challenge of concept drift, where data distributions evolve over time, leading to a decline in forecast model performance. Existing solutions are based on online learning, which continually organize recent time series observations as new training samples and update model parameters according to the forecasting feedback on recent data. However, they overlook a critical issue: obtaining ground-truth future values of each sample should be delayed until after the forecast horizon. This delay creates a temporal gap between the training samples and the test sample. Our empirical analysis reveals that the gap can introduce concept drift, causing forecast models to adapt to outdated concepts. In this paper, we present \textsc{Proceed}, a novel proactive model adaptation framework for online time series forecasting. \textsc{Proceed} first operates by estimating the concept drift between the recently used training samples and the current test sample. It then employs an adaptation generator to efficiently translate the estimated drift into parameter adjustments, proactively adapting the model to the test sample. To enhance the generalization capability of the framework, \textsc{Proceed} is trained on synthetic diverse concept drifts. We conduct extensive experiments on five real-world datasets across various forecast models. The empirical study demonstrates that our proposed \textsc{Proceed} brings more performance improvements than the state-of-the-art online learning methods, significantly facilitating forecast models' resilience against concept drifts.