3919 papers
The paper introduces GeoVisA11y, an open-source, LLM-based system that enables screen-reader users to interact with geovisualizations through natural language queries, validated by user studies demonstrating its effectiveness in bridging accessibility gaps and revealing distinct interaction patterns.
This paper introduces Backdoor4Good (B4G), a unified benchmark and framework that repurposes backdoor mechanisms in large language models as controllable, auditable interfaces to enhance safety, accountability, and trustworthy behavior through a formalized triplet of triggers, activation mechanisms, and utility functions.
This paper proposes a dual spatial-scale UAV network optimization framework that combines exact potential game algorithms for link configuration and deployment with a large language model to dynamically generate utility weights, thereby enhancing adaptability and performance in terms of energy efficiency, latency, and throughput.
This paper reveals a critical expectation gap in the freelance economy where workers often withhold AI use due to a mistaken belief that clients can detect it, while clients prefer proactive disclosure and lack clear policies, ultimately highlighting the urgent need for standardized guidelines to rebuild trust and accountability in AI-mediated work.
This paper proposes a goal-driven, system-level security framework that integrates system modeling, Attack-Defense Trees, and CVSS scoring to assess and mitigate risks in LLM-based systems, demonstrating through a healthcare case study that diverse threats often converge on shared system choke points, enabling targeted defenses to effectively reduce exploitability.
This paper proposes a human-centred out-of-distribution spectrum that redefines perceptual difficulty based on human accuracy to enable principled comparisons of model-human error alignment, revealing that while vision-language models show the most consistent alignment across conditions, the relative performance of CNNs and ViTs depends on the specific regime of perceptual challenge.
SIGMAE is a novel foundation model for multispectral remote sensing that enhances Masked Autoencoder pretraining by incorporating domain-specific spectral indices to guide dynamic token masking toward semantically salient regions, thereby achieving superior performance across various downstream tasks compared to existing geospatial models.
This paper introduces MonoSTL, a selective transfer learning framework that addresses the negative transfer caused by modality gaps in cross-modality distillation for monocular 3D object detection by employing similar architectures and novel depth-aware selective distillation modules to effectively transfer LiDAR depth information to image-based networks, achieving state-of-the-art performance on KITTI and NuScenes benchmarks.
This paper introduces the ThingiPrint dataset and a contrastive fine-tuning approach that enables the classification of novel 3D-printed objects using their CAD models without requiring model retraining, thereby addressing a critical bottleneck in automating industrial post-production workflows.
FedEU is a novel federated learning framework that enhances remote sensing image segmentation by integrating evidential uncertainty quantification and client-specific feature embeddings to guide adaptive global aggregation, thereby improving model robustness and reliability across heterogeneous distributed datasets.
This paper reveals that MCP-based AI systems are fundamentally insecure due to a lack of caller identity authentication, which allows persistent authorization states and missing per-tool checks to enable unauthorized access to sensitive operations by untrusted callers.
This paper introduces Early Vision-Language Fusion (EVLF), a plug-and-play method that aligns textual and visual embeddings early in the diffusion process to overcome the visual dominance issues of late-stage guidance, thereby generating semantically faithful and visually coherent synthetic datasets that improve downstream classification accuracy.
This paper proposes GSAT, a self-supervised framework that leverages anomaly detection within a positive hypersphere in latent space to reliably estimate traversability for diverse terrains without requiring explicit negative supervision or additional prototypes.
The paper introduces HSC-VLA, a hierarchical framework that enhances robust bimanual manipulation in dense clutter by decoupling high-level semantic reasoning from low-level execution through explicit scene-clearing, achieving significantly higher success rates than monolithic baselines in complex long-horizon tasks.
This paper proposes a Multi-Modal Decouple and Recouple Network that enhances robust 3D object detection under data corruption by explicitly separating BEV features into invariant and specific components to enable cross-modal compensation, followed by an adaptive fusion of three specialized experts tailored to different corruption scenarios.
This paper introduces RobustSCI, a pioneering framework that shifts snapshot compressive imaging from simple reconstruction to robust restoration by proposing a novel network architecture and a large-scale benchmark to effectively recover pristine scenes from real-world degraded measurements caused by motion blur and low light.
The paper proposes RayD3D, a novel cross-modal distillation framework that transfers depth knowledge specifically along the camera-to-object ray to filter out irrelevant LiDAR information, thereby significantly enhancing the robustness of multi-view 3D object detection models against real-world data corruptions without increasing inference costs.
DocCogito is a unified framework for document understanding that aligns global layout perception with structured, region-grounded reasoning through a lightweight layout tower and a deterministic Visual-Semantic Chain, achieving state-of-the-art performance on multiple benchmarks by enforcing systematic coupling between layout priors and evidence-based reasoning.
This paper proposes the Hierarchical Autonomy Evolution (HAE) framework to address critical security vulnerabilities in evolving AI agents by categorizing threats and defenses across three tiers: Cognitive, Execution, and Collective Autonomy.
This paper proposes AMR-CCR, an anchored modular retrieval framework with script-conditioned injection and multi-prototype dictionaries to address the challenges of continual, class-incremental ancient Chinese character recognition, accompanied by the new EvoCON benchmark for systematic evaluation.