Few-shot object detection (FSOD) in high-resolution remote sensing (RS) imagery remains challenging due to scarce annotations, large intra-class variability, and high visual similarity between categories, which together limit the generalization ability of convolutional neural network (CNN)-based detectors. To address this issue, we explore leveraging large vision-language models (LVLMs) for FSOD in RS. We propose a two-stage, parameter-efficient fine-tuning framework with hierarchical prompting that adapts Qwen3-VL for object detection. In the first stage, low-rank adaptation (LoRA) modules are inserted into the vision and text encoders and trained jointly with a Detection Transformer (DETR)-style detection head on fully annotated base classes under three-level hierarchical prompts. In the second stage, the vision LoRA parameters are frozen, the text encoder is updated using $K$-shot novel-class samples, and the detection head is partially frozen, with selected components refined using the same three-level hierarchical prompting scheme. To preserve base-class performance and reduce class confusion, we further introduce knowledge distillation and semantic consistency losses. Experiments on the DIOR and NWPU VHR-10.v2 datasets show that the proposed method consistently improves novel-class performance while maintaining competitive base-class accuracy and surpasses existing baselines, demonstrating the effectiveness of integrating hierarchical semantic reasoning into LVLM-based FSOD for RS imagery.

Unsupervised change detection (UCD) from heterogeneous bitemporal optical–SAR imagery is challenging due to modality discrepancy, speckle/illumination variations, and the absence of change annotations. We propose MV-S2CD, a vision foundation model (VFM)-based framework that learns a modality-bridged latent space and produces dense change maps in a fully unsupervised manner. To robustly adapt pretrained VFM priors to heterogeneous inputs with minimal task-specific parameters, MV-S2CD incorporates lightweight modality-specific adapters and parameter-efficient low-rank adaptation (LoRA) in high-level layers. A shared projector embeds the two observations into a common geometry, enabling consistent cross-modal comparison and reducing sensor-induced domain shift. Building on the bridged representation, we design a dual-branch change reasoning module that decouples structure-sensitive cues from semantic-consistency cues: a structure pathway preserves fine boundaries and local variations, while a semantic-consistency pathway employs reliability gating and multi-scale context aggregation to suppress pseudo-changes caused by modality-specific nuisances and residual misregistration. For label-free optimization, we develop a difference-centric self-supervision scheme with two perturbation views and reliability-guided pseudo-partitioning, jointly enforcing pseudo-unchanged invariance, pseudo-changed/unchanged separability, and sparsity and edge-preserving regularization. Experiments on three heterogeneous optical–SAR benchmarks demonstrate that MV-S2CD consistently improves the Precision–Recall trade-off and achieves state-of-the-art performance among unsupervised baselines, while remaining backbone-flexible and efficient.

Unsupervised change detection (UCD) from heterogeneous bitemporal optical–SAR imagery is challenging due to modality discrepancy, speckle/illumination variations, and the absence of change annotations. We propose MV-S2CD, a vision foundation model (VFM)-based framework that learns a modality-bridged latent space and produces dense change maps in a fully unsupervised manner. To robustly adapt pretrained VFM priors to heterogeneous inputs with minimal task-specific parameters, MV-S2CD incorporates lightweight modality-specific adapters and parameter-efficient low-rank adaptation (LoRA) in high-level layers. A shared projector embeds the two observations into a common geometry, enabling consistent cross-modal comparison and reducing sensor-induced domain shift. Building on the bridged representation, we design a dual-branch change reasoning module that decouples structure-sensitive cues from semantic-consistency cues: a structure pathway preserves fine boundaries and local variations, while a semantic-consistency pathway employs reliability gating and multi-scale context aggregation to suppress pseudo-changes caused by modality-specific nuisances and residual misregistration. For label-free optimization, we develop a difference-centric self-supervision scheme with two perturbation views and reliability-guided pseudo partitioning, jointly enforcing pseudo-unchanged invariance, pseudo-changed/unchanged separability, and sparsity and edge-preserving regularization. Experiments on three heterogeneous optical–SAR benchmarks demonstrate that MV-S2CD consistently improves the precision–recall trade-off and achieves state-of-the-art performance among unsupervised baselines, while remaining backbone-flexible and efficient.

Post-disaster emergency communication recovery is not merely a link-repair task but a high-level planning problem constrained by service priorities, inter-object dependencies, resource budgets, and time windows. Existing restoration optimization methods generally rely on fully structured inputs, whereas direct large language model (LLM) planning may produce fluent candidates that violate encoded prerequisites, stage-order relations, budget limits, or temporal constraints. To address this challenge, we propose ICG-Restore, an intent-constrained, graph-enhanced LLM planning framework with rule-consistent minimal-edit repair. ICG-Restore transforms mixed restoration requests and structured network observations into task packages that can be checked for validator-level feasibility under an encoded high-level constraint model and evaluated by downstream abstract executors or schedulers. The framework compiles natural-language requests, structured observations, and operational rules into a task-intent object; retrieves task-relevant context from a heterogeneous scenario graph and a restoration knowledge graph; generates stage-wise restoration candidates; and applies bounded local corrections to candidates that violate encoded constraints. In this paper, “minimal-edit” is a descriptive label for a bounded local repair principle that prioritizes less disruptive corrections. Candidates accepted by the validators are evaluated and ranked by a safety-aware agent executor operating in an abstract restoration action space. Experiments on controlled abstract topologies covering three scales, four restoration tasks, and five environmental evolution modes show that ICG-Restore improves validator-level constraint satisfaction and benchmark-estimated recovery utility. Compared with Direct-LLM, it improves CSR and CRS by 1.99% and 24.56%, respectively; benchmark-specific WCTC@5 structural-alignment diagnostic increases by 38.87%.

The growing affordability, autonomy, and swarming of small unmanned aerial vehicles (UAVs) turn low-altitude defense from single-shot interception into a multi-node cooperative decision problem, in which the loss of sensing, coordination, or engagement nodes breaks the closed loops linking them. This study formulates their recovery as the dynamic reconfiguration of cooperative counter-UAV task chains. Given a pre-disturbance plan and a set of failed defending nodes, reconfiguration is modeled as a constrained bi-objective optimization balancing recovered engagement effectiveness against the change to the baseline plan and is solved by Multi-Agent Heuristic Evolution (MAHE), an automated heuristic design framework whose evolution, coordinator, repair, and reflection agents—driven by a large language model—evolve scoring heuristics for a fixed reconfiguration solver. Across instances of varying scale and under light-to-heavy node loss conditions, MAHE outperforms both a single-agent heuristic design counterpart and a range of hand-crafted solvers: on ten held-out test instances spanning 8–320 targets it attains the highest overall normalized hypervolume (0.947, versus 0.935 for the single-agent counterpart and 0.30–0.45 for the hand-crafted solvers) and the best mean rank (1.43 of six methods, $p<{10}^{-5}$); the hand-crafted solvers lose most of their solution quality as the problem grows, whereas MAHE preserves it and sustains high recovery at a nearly constant reconfiguration cost. An ablation confirms that its agents contribute complementary gains. These simulation results indicate that automatically generated, reconfiguration-specific heuristics offer a scalable algorithmic foundation for dynamic, heterogeneous, and constraint-intensive counter-UAV task-chain reconfiguration.

Accurate long-term forecasting of Quality of Transmission (QoT) is critical for the proactive operation and condition-aware management of dynamic elastic optical networks. However, the evolution of QoT is governed by multi-scale dynamics, including slow equipment aging, periodic operating variations, and short-term channel fluctuations, which a single temporal model struggles to capture jointly. To address this issue, we propose PA-TCN-Informer, a decomposition-driven parallel forecasting framework for long-horizon QoT prediction. The proposed framework first applies Seasonal-Trend decomposition using Loess (STL) to separate the Q-factor sequence into trend, seasonal, and residual components, and then employs Variational Mode Decomposition (VMD) to further resolve the residual into short-term fluctuation modes. The decomposed components, together with physical-layer monitoring features, are fed into a parallel TCN–Informer architecture, in which the TCN branch captures local temporal patterns while the Informer branch models long-range dependencies; the two streams are subsequently fused. We evaluate the proposed framework through Optuna-based hyperparameter optimization, STL/VMD sensitivity analysis, decomposition-method comparison, multi-seed baseline comparison with statistical testing, and zero-shot leave-one-dataset-out cross-domain evaluation. On the primary dataset, PA-TCN-Informer achieves the best overall forecasting accuracy among the compared models and reduces MAE by 2.2% relative to the serial TCN–Informer. In addition, the staged STL-VMD preprocessing alone yields a 60.8% reduction in MAE compared with raw inputs, confirming the value of physically interpretable multi-scale decomposition. In the zero-shot cross-domain setting, PA-TCN-Informer remains competitive across target domains. These results demonstrate that the proposed framework provides an effective and interpretable approach to QoT forecasting, and they further indicate that topology-aware modeling is a promising direction for improving cross-domain generalization.