Recent advancements in visual autoregressive models (VAR) have demonstrated their effectiveness in image generation, highlighting their potential for real-world image super-resolution (Real-ISR). However, adapting VAR for ISR presents critical challenges. The next-scale prediction mechanism, constrained by casual attention, fails to fully exploit global low-quality (LQ) context, resulting in blurry and inconsistent high-quality (HQ) outputs. Additionally, error accumulation in the iterative prediction severely degrades coherence in ISR task. To address these issues, we propose VARestorer, a simple yet effective distillation framework that transforms a pre-trained text-to-image VAR model into a one-step ISR model. By leveraging distribution matching, our method eliminates the need for iterative refinement, significantly reducing error propagation and inference time. Furthermore, we introduce pyramid image conditioning with cross-scale attention, which enables bidirectional scale-wise interactions and fully utilizes the input image information while adapting to the autoregressive mechanism. This prevents later LQ tokens from being overlooked in the transformer. By fine-tuning only 1.2\% of the model parameters through parameter-efficient adapters, our method maintains the expressive power of the original VAR model while significantly enhancing efficiency. Extensive experiments show that VARestorer achieves state-of-the-art performance with 72.32 MUSIQ and 0.7669 CLIPIQA on DIV2K dataset, while accelerating inference by 10 times compared to conventional VAR inference.

In this paper, we propose an autonomous robot packing system named RoboPacker designed to tightly store cluttered general objects into shipping boxes with high space utilization, which is a fundamental process in numerous industrial applications. However, achieving tight packaging for general objects often demands significant labor from human packers, particularly in high-throughput scenes. Compared to existing robot packing approaches, RoboPacker effectively overcomes challenges such as diverse object appearances, severe occlusion, and crowded packing spaces. Specifically, we propose an open-vocabulary shape estimation method to reconstruct complete point clouds for cluttered objects. We also design effective interactions with object clutter to gather informative visual clues for shape estimation under high uncertainty. Additionally, we introduce a hierarchical reinforcement learning framework to optimize packing order, location, and orientation for maximum space utilization. The robotic packing system integrates these techniques with feasible manipulation methods for real-world implementation. In this way, RoboPacker achieves efficient packing of novel and irregular objects, which is more suitable for real deployment environments. The Real-world experiments demonstrate RoboPacker can tightly pack 20 densely cluttered everyday objects from 8 seen and 4 novel classes into the 40x40x20 cm shipping box with a 73.3% success rate.

In this paper, we propose a hyperparameter-specialized adaptive fingerprinting framework named AdaParse for model reverse engineering, which aims at predicting hyperparameters of interest in generative models from the given AI-generated images. Existing methods rely on a single coarse model fingerprint that is originally designed for model-level attribution, which makes it difficult to distinguish fine-grained traces corresponding to different hyperparameter configurations in a multitude of generative models. To address this, our AdaParse dynamically responds to instance-level variations by estimating hyperparameter-specific fingerprints via personalizing estimation networks tailored for each input image. Specifically, our approach simultaneously learns two-branch hypernetworks that balance instance-aware and model-agnostic prior knowledge for fingerprint generation. To enable efficient network personalization, we further propose a Broadcasted Fusion module that transforms condensed feature codes into adaptive parameters through factorized weight generation with enhanced representative capacity. Extensive experiments on the large-scale public dataset across 123 generative models demonstrate that our approach outperforms previous state-of-the-art methods. Code available at https://github.com/lizhuoxun/AdaParse/.

In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To address this, most existing methods learn a network to prune redundant visual tokens using certain training data. Differently, we propose a text-guided training-free token optimization mechanism dubbed SparseVLM without fine-tuning costs. Given that visual tokens complement text tokens in VLM's linguistic reasoning, we select relevant text tokens to rate the significance of visual tokens using self-attention matrices and, then, prune visual tokens using the proposed strategy to maximize sparsity while retaining information. In particular, we introduce a rank-based strategy to adaptively determine the sparsification ratio for each layer, alongside a token recycling method that compresses pruned tokens into more compact representations. However, the Attention Gravity and Attention Sink phenomena undermine the sparsification reference of SparseVLM: text-visual alignment. To address this, we introduce improved text-visual attention patterns to enhance the fidelity of query-aware vision token selection. First, we correct the Attention Gravity effect, where positional encodings induce disproportionately high attention to vision tokens positioned near textual tokens. We further mitigate the Attention Sink by selecting priority attention heads that suppress the excessive attention absorbed by semantically irrelevant vision tokens. The two parts refine the text-visual alignment from both the token and head perspectives. Finally, for video understanding tasks, we propose Temporal-Balanced Sparsification, complementing spatial relevance with temporal diversity to reduce cross-frame redundancy. Extensive experiments on 23 widely used image and video understanding tasks across 7 vision-language models demonstrate the effectiveness of our SparseVLM+ framework. For example, equipping LLaVA with SparseVLM+ yields a 57.1% reduction in FLOPs and a 38.4% decrease in CUDA latency, while preserving 99.6% of its original accuracy on average. Our code is available at https://github.com/Gumpest/SparseVLMs.

Embodied visuomotor models, including Diffusion Policy (DP) and Vision-Language-Action (VLA) models, have demonstrated promising performance on robotic manipulation benchmarks. However, their potential remains fundamentally constrained by the scarcity of large-scale embodied trajectory datasets, leading to insufficient compositional generalization in out-of-distribution (OOD) scenarios with limited capability to capture reusable skill structures. To address this limitation, we propose Skill-Based Memory (SkillMemo) framework that implicitly decomposes long-horizon demonstrations into latent atomic skills and integrates skill-level features into a dynamic episodic memory bank for solving compositional tasks. Specifically, we first introduce an expert-guided trajectory segmentation module built upon a Mixture-of-Experts (MoE) architecture, which implicitly partitions trajectories into distinct skill primitives represented by learned gating coefficients. We further design a skill-level episodic memory architecture that stores compact skill representations as retrievable key-value pairs. During inference, the memory bank retrieves the most relevant skill primitives which are subsequently fused with the model's current gating distribution, providing a robust contextual prior to refine action predictions. Extensive experiments on the simulation benchmark and real-world manipulation tasks demonstrate that SkillMemo consistently enhances both DP and VLA backbones, achieving state-of-the-art performance and outperforming π_0.5, while exhibiting strong compositional generalization to unseen task configurations.

Recent generative models can produce high-fidelity videos, yet they often exhibit 3D spatial geometric inconsistencies. Existing evaluation methods fail to accurately characterize these inconsistencies: fidelity-centric metrics like FVD are insensitive to geometric distortions, while consistency-focused benchmarks often penalize valid foreground dynamics. To address this gap, we introduce SGC, a metric for evaluating 3D Spatial Geometric Consistency in dynamically generated videos. We quantify geometric consistency by measuring the divergence among multiple camera poses estimated from distinct local regions. Our approach first separates static from dynamic regions, then partitions the static background into spatially coherent sub-regions. We predict depth for each pixel, estimate a local camera pose for each subregion, and compute the divergence among these poses to quantify geometric consistency. Experiments on real and generative videos demonstrate that SGC robustly quantifies geometric inconsistencies, effectively identifying critical failures missed by existing metrics.

Spatial generalization is critical for imitation-learned manipulation policies, but achieving it typically requires scaling demonstrations across diverse object poses, robot configurations, and camera viewpoints. Data augmentation from a few source demonstrations offers a practical alternative to costly real-world collection. Simulation-based augmentation can create controllable variation, but requires complex environment and object setup and may introduce a sim-to-real gap. Recent real-to-real methods avoid these issues by jointly editing 3D observations and action trajectories from real demonstrations, yet they still rely on strong 3D scene parsing and geometry completion, and often produce observations tailored to 3D pointcloud policies rather than RGB-based 2D policies. We propose R2RDreamer, a real-to-real demonstration augmentation framework that preserves the geometric consistency of 3D action-observation editing while moving visual completion to 2D video space. Specifically, R2RDreamer first performs lightweight 3D augmentation by editing incomplete object pointclouds and end-effector trajectories in a shared 3D frame; it then projects the edited scene into masked image-space control videos with occlusion-aware reasoning and uses a dense-control image-to-video model to complete temporally coherent RGB observations. Experiments on spatially shifted manipulation tasks with both 2D diffusion-style policies and vision-language-action policies show that R2RDreamer improves spatial generalization from limited source demonstrations, with analyses validating the contributions of 3D editing, occlusion-aware projection, and video completion.

World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a common design in existing WAMs is to explicitly generate future videos at inference time, incurring substantial computational overhead and hindering real-time closed-loop deployment. GigaWorld-Policy addresses this issue with an action-centered formulation, where future visual dynamics are used during training while action-only decoding is used at inference time. Building upon this framework, we present GigaWorld-Policy-0.5, an enhanced action-centered WAM designed for more efficient robot control. During pretraining, GigaWorld-Policy-0.5 adopts a mixed Action-Conditioned World Modeling (AC-WM) and WAM training strategy. This strengthens the coupling between visual dynamics and robot actions and improves the transferability of action representations for downstream policy learning. For efficient inference, GigaWorld-Policy-0.5 introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts, reducing active computation during action-only inference and achieving 85 ms inference latency on a local RTX 4090 setup. In addition, we employ an agent-based AutoResearch pipeline to systematically search training configurations, enabling more efficient identification of optimal experimental setups while reducing the time and manual intervention required for hyperparameter tuning. Experiments and ablations show that GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control.

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, it still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera configurations. To bridge this gap, we propose a Visual Geometry Transformer specifically designed for autonomous Driving (DVGT), which reconstructs a global dense 3D point map from a sequence of unposed multi-view visual inputs. We first extract visual features for each image and employ alternating intra-view local attention, cross-view spatial attention, and cross-frame temporal attention to infer geometric relations across images. Finally, we use multiple heads to decode a global point map in the ego coordinate of the first frame and the ego pose for each frame. Our DVGT directly predicts metric-scaled geometry from image sequences, eliminating the need for post-alignment with external sensors. Trained on a large mixture of driving datasets, including nuScenes, OpenScene, Waymo, KITTI, and DDAD, DVGT significantly outperforms the other geometry prediction models on various scenarios.

This paper proposes an adaptive margin contrastive learning method for 3D semantic segmentation on point clouds. Most existing methods use equally penalized objectives, which ignore the per-point ambiguities and less discriminated features stemming from transition regions. However, as highly ambiguous points may be indistinguishable even for humans, their manually annotated labels are less reliable, and hard constraints over these points would lead to sub-optimal models. To address this, we first design AMContrast3D, a method comprising contrastive learning into an ambiguity estimation framework, tailored to adaptive objectives for individual points based on ambiguity levels. As a result, our method promotes model training, which ensures the correctness of low-ambiguity points while allowing mistakes for high-ambiguity points. As ambiguities are formulated based on position discrepancies across labels, optimization during inference is constrained by the assumption that all unlabeled points are uniformly unambiguous, lacking ambiguity awareness. Inspired by the insight of joint training, we further propose AMContrast3D++ integrating with two branches trained in parallel, where a novel ambiguity prediction module concurrently learns point ambiguities from generated embeddings. To this end, we design a masked refinement mechanism that leverages predicted ambiguities to enable the ambiguous embeddings to be more reliable, thereby boosting segmentation performance and enhancing robustness. Experimental results on 3D indoor scene datasets, S3DIS and ScanNet, demonstrate the effectiveness of the proposed method. Code is available at https://github.com/YangChenApril/AMContrast3D.

Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and actions remain underexplored, especially for general-purpose scenarios and various forms of actions. To bridge this gap, we introduce Astra, an interactive general world model that generates real-world futures for diverse scenarios (e.g., autonomous driving, robot grasping) with precise action interactions (e.g., camera motion, robot action). We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations and support streaming outputs. We use a noise-augmented history memory to avoid over-reliance on past frames to balance responsiveness with temporal coherence. For precise action control, we introduce an action-aware adapter that directly injects action signals into the denoising process. We further develop a mixture of action experts that dynamically route heterogeneous action modalities, enhancing versatility across diverse real-world tasks such as exploration, manipulation, and camera control. Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions. Experiments across multiple datasets demonstrate the improvements of Astra in fidelity, long-range prediction, and action alignment over existing state-of-the-art world models.

Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects and challenging scenarios with distractors, occlusion, and nonlinear motion. Recent vision foundation models, exemplified by SAM 2, learn strong video understanding priors from large-scale pretraining and offer a promising foundation for building more robust and generalizable trackers. However, directly applying SAM 2 to VOT remains suboptimal, as it does not explicitly model target motion dynamics or enforce geometric and semantic consistency across frames, both of which are essential for reliable tracking. To address this issue, we propose SAMOSA, a new tracking framework that adapts SAM 2 to complex VOT scenarios by explicitly leveraging motion, geometry, and semantic cues. Specifically, we introduce a lightweight nonlinear motion predictor to model target dynamics and guide mask selection as well as memory filtering. We further exploit semantic cues to detect target shifts and recover from tracking failures, while geometric cues are incorporated as structural constraints to improve tracking stability. In this way, SAMOSA bridges the gap between the implicit video understanding prior of SAM 2 and explicit tracking-oriented modeling. Extensive experiments show that SAMOSA consistently outperforms state-of-the-art SAM 2–based approaches on general benchmarks, demonstrates stronger generalization than supervised VOT methods, and achieves substantial gains on anti-UAV datasets, which typify complex nonlinear motion scenarios. Our code is available at https://github.com/DurYi/SAMOSA.

Video diffusion models, trained on large-scale datasets, naturally capture correspondences of shared features across frames. Recent works have exploited this property for tasks such as optical flow prediction and tracking in a zero-shot setting. Motivated by these findings, we investigate whether supervised training can more fully harness the tracking capability of video diffusion models. To this end, we propose Moaw, a framework that unleashes motion awareness for video diffusion models and leverages it to facilitate motion transfer. Specifically, we train a diffusion model for motion perception, shifting its modality from image-to-video generation to video-to-dense-tracking. We then construct a motion-labeled dataset to identify features that encode the strongest motion information, and inject them into a structurally identical video generation model. Owing to the homogeneity between the two networks, these features can be naturally adapted in a zero-shot manner, enabling motion transfer without additional adapters. Our work provides a new paradigm for bridging generative modeling and motion understanding, paving the way for more unified and controllable video learning frameworks.

Deep learning has profoundly impacted society, yet the inherent nature of deep neural networks hinders further application to high-reliability industries. To demystify these closed-boxes, numerous works attempt to improve the explainability by observing or impacting internal variables of the models. However, existing methods rely on heuristics without rigorous theoretical foundations, often requiring intricate model modifications or redesigns. This work first formalizes two fundamental properties of explainability: alignment and invertibility, serving as theoretical pillars for rigorous interpretability analysis. Building on these, we introduce Bort, a plug-and-play optimizer that enforces Boundedness and orthogonality constraints on model parameters to improve explainability. These constraints are theoretically derived from the alignment and invertibility principles. Considering conventional optimizers can not leverage data features for precise attribution, we present a data-aware extension, termed DBort, which integrates an auxiliary loss term. Intriguingly, in the linear case, DBort converges to Principal Component Analysis (PCA). Our in-depth analysis of penalty term design reveals that $l_{1}$l1-based penalties provide a more stringent adherence to the imposed constraints compared to their $l_{2}$l2 counterparts. Our experiments involve reconstructing and backtracking through the optimized model representations, which reveal a marked enhancement in explainability. Furthermore, leveraging Bort, we successfully synthesize explainable adversarial examples without additional training. Notably, Bort consistently improves the classification accuracy across diverse architectures, including ResNet and DeiT, on benchmark datasets such as MNIST, CIFAR-10, and ImageNet.

Recent progress in vision Transformers exhibits great success in various tasks driven by the new spatial modeling mechanism based on dot-product self-attention. In this paper, we show that the key ingredients behind the vision Transformers, namely input-adaptive, long-range and high-order spatial interactions, can also be efficiently implemented with a convolution-based framework. We present the Recursive Gated Convolution (${\mathit{g}}^{\mathit{n}}$gnConv) that performs high-order spatial interactions with gated convolutions and recursive designs. The new operation is highly flexible and customizable, which is compatible with various variants of convolution and extends the two-order interactions in self-attention to arbitrary orders without introducing significant extra computation. ${\mathit{g}}^{\mathit{n}}$gn Conv can serve as a plug-and-play module to improve various vision Transformers and convolution-based models. Based on the proposed operation, we construct a new family of generic vision backbones for various visual modalities and tasks, including HorNet and HorFPN for image recognition, Hor3D for point cloud analysis, and HorCLIP for vision-language modeling. For image recognition, we propose HorNet as a stronger visual encoder, where we conduct extensive experiments on ImageNet classification, COCO object detection, and ADE20K semantic segmentation. HorNet outperforms Swin Transformers and ConvNeXt by a significant margin with similar overall architecture and training configurations. HorNet also shows favorable scalability to more training data and larger model sizes. Apart from image encoders, we also show ${\mathit{g}}^{\mathit{n}}$gnConv can be applied to task-specific decoders and consistently improve dense prediction performance with less computation. For point cloud analysis, we design Hor3D, demonstrating the efficacy of high-order interactions for unstructured point cloud data through experiments on challenging 3D semantic segmentation tasks in S3DIS and ScanNet V2. In vision-language modeling, our proposed HorCLIP surpasses mainstream Vision Transformer and ConvNeXt architectures with shorter training schedules on ImageNet zero-shot classification and shows remarkably higher performance on vision-language dense representation tasks on COCO Panoptic datasets. Our results demonstrate that ${\mathit{g}}^{\mathit{n}}$gnConv with high-order spatial interactions can be a new basic operation for visual modeling that effectively combines the merits of both vision Transformers and CNNs.

GUI grounding is a critical capability for vision-language models (VLMs) that enables automated interaction with graphical user interfaces by locating target elements from natural language instructions. However, grounding on GUI screenshots remains challenging due to high-resolution images, small UI elements, and ambiguous user instructions. In this work, we propose AdaZoom-GUI, an adaptive zoom-based GUI grounding framework that improves both localization accuracy and instruction understanding. Our approach introduces an instruction refinement module that rewrites natural language commands into explicit and detailed descriptions, allowing the grounding model to focus on precise element localization. In addition, we design a conditional zoom-in strategy that selectively performs a second-stage inference on predicted small elements, improving localization accuracy while avoiding unnecessary computation and context loss on simpler cases. To support this framework, we construct a high-quality GUI grounding dataset and train the grounding model using Group Relative Policy Optimization (GRPO), enabling the model to predict both click coordinates and element bounding boxes. Experiments on public benchmarks demonstrate that our method achieves state-of-the-art performance among models with comparable or even larger parameter sizes, highlighting its effectiveness for high-resolution GUI understanding and practical GUI agent deployment.

In this paper, we propose view-dependent projection (VDP) to facilitate point cloud segmentation, designing efficient 3D-to-2D mapping that dynamically adapts to the spatial geometry from view variations. Existing projection-based methods leverage view-independent projection in complex scenes, relying on straight lines to generate direct rays or upward curves to reduce occlusions. However, their view independence provides projection rays that are limited to pre-defined parameters by human settings, restricting point awareness and failing to capture sufficient projection diversity across different view planes. Although multiple projections per view plane are commonly used to enhance spatial variety, the projected redundancy leads to excessive computational overhead and inefficiency in image processing. To address these limitations, we design a framework of VDP to generate data-driven projections from 3D point distributions, producing highly informative single-image inputs by predicting rays inspired by the adaptive behavior of fireworks. In addition, we construct color regularization to optimize the framework, which emphasizes essential features within semantic pixels and suppresses the non-semantic features within black pixels, thereby maximizing 2D space utilization in a projected image. As a result, our approach, PointVDP, develops lightweight projections in marginal computation costs. Experiments on S3DIS and ScanNet benchmarks show that our approach achieves competitive results, offering a resource-efficient solution for semantic understanding.

Point clouds, as an unstructured set of points, have emerged as a crucial data format in modern 3D deep learning tasks, facilitating applications ranging from object recognition to scene understanding. However, traditional point cloud encoding methods grounded in voxelization or grouping strategies often suffer from inefficiencies and ambiguities during local point cloud processing. These limitations can hinder the extraction of fine-grained features and impact the overall performance of 3D learning models. Notably, compact representations, such as the neural field representation employed in 3D shape reconstruction, have demonstrated remarkable capabilities in capturing the structural integrity and intricate details of 3D objects. Nevertheless, the utilization of these advanced representations in discriminative tasks remains largely unexplored territory. In response to these challenges and opportunities, we propose Point2Seq, a novel point cloud encoding method. Point2Seq constructs a new representation of point clouds by leveraging serialized and discrete encoding techniques. This approach transforms point clouds into a grid-based format, which not only enables efficient spatial interpolation but also facilitates the expansion of the receptive field for downstream tasks, thereby enhancing the model’s ability to capture context and spatial relationships. To comprehensively assess the effectiveness of Point2Seq, we conduct extensive evaluations on a diverse set of canonical object-level point cloud benchmarks. Our experiments cover a wide spectrum of tasks, including low-level tasks like point cloud completion, high-level tasks such as classification and part segmentation, as well as few-shot learning scenarios. The results demonstrate that Point2Seq achieves state-of-the-art performance across these tasks. Additionally, the reduced noise in the input data allows our representation to converge more rapidly during downstream task training, further underscoring its superiority. The code for Point2Seq will be publicly released to promote reproducibility and further research in this area.

Evaluating embodied robot foundation models remains a critical bottleneck; unlike large language models efficiently assessed via digital benchmarks, robotic policies require slow, costly real-world rollouts limited by hardware and human supervision, which has driven interest in world models as surrogate policy evaluators, yet the key properties that make a world model reliable for policy assessment remain poorly understood. This work presents a systematic study of world models for robotic policy evaluation and introduces WMBench, a benchmark constructed from real-robot teleoperation data and matched policy rollouts covering diverse manipulation tasks to enable controlled comparisons across model families, action encodings, rollout horizons, and evaluation metrics. Using WMBench, we analyze 7 video world models, 4 action representation schemes, and over 324,000 simulated policy rollouts paired with real robot executions, further enriching our analysis with large-scale community submissions from the CVPR 2026 GigaBrain Challenge, curated synthetic trajectories, and a training videos spanning more than 12,000 hours. Our experiments deliver three core insights: evaluator quality is dominated by long-horizon, action-faithful rollout consistency rather than short-term visual realism; pretraining gains stem not only from data scale but from balancing general world knowledge with robot-specific controllability; and architectural choices including action encoding, memory design, and evaluator-focused post-training strongly determine alignment with real-world robot behavior. Drawing on these results, we derive a practical design roadmap and realize it in GigaWorld-1, a world model specially optimized for policy evaluation, and we fully release our code, models, datasets, and toolkits to advance scalable evaluation research for embodied foundation models.

With the widespread application of drones in recent years, object detection of aerial images has attracted increasing attention, especially open-vocabulary aerial detection which is not restricted to predefined categories. Due to the scarcity of drone's viewpoint images and their significant differences from natural images, it is difficult to achieve satisfying results by directly applying vanilla open-vocabulary detection methods designed for natural scenarios. Some studies propose to transfer knowledge from pre-trained models by using lightweight networks or generating pseudo labels, but they tend to rely on models trained on natural images, neglecting the potential of foundation models specifically tailored for remote sensing and aerial imagery. To address this limitation, we propose DisDop, a unified framework that systematically distills multi-level domain priors from remote sensing foundation models (e.g., RemoteCLIP and DINOv3) into a lightweight detector. Specifically, we first distill visual priors through a teacher fusion strategy that combines RemoteCLIP's cross-modal alignment capability with DINOv3's fine-grained local feature extraction ability, transferring their complementary strengths to the detector's backbone. Second, we distill textual priors embedded in RemoteCLIP's text encoder by explicitly modeling inter-category semantic relationships, while incorporating global contextual priors to enhance local feature representation for small objects. Through this multi-level prior distillation framework, our DisDop achieves new state-of-the-art performance on open-vocabulary aerial detection benchmarks. Extensive ablation analysis also demonstrates the rationality and effectiveness of our proposed modules.