Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606.01600v2 Announce Type: replace-cross Abstract: Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and saf...
arXiv:2606.06037v3 Announce Type: replace-cross Abstract: Large audio language models (LALMs) are increasingly deployed in real-world applications, yet their safety alignment is still primarily evalu...
arXiv:2608.28674v1 Announce Type: new Abstract: Multi-exposure is an efficient way to capture real-world high-dynamic-range (HDR) scenes. However, HDR imaging suffers from severe ghosting artifacts i...
arXiv:2608.28681v1 Announce Type: new Abstract: Probability calibration aligns model confidence with predictive accuracy, enabling clinicians to identify unreliable segmentation regions. This alignme...
arXiv:2608.28762v1 Announce Type: new Abstract: Recent advances in visual question answering (VQA) and multimodal large language models (MLLMs) have enabled natural-language reasoning over traffic sc...
arXiv:2608.28891v1 Announce Type: new Abstract: Pixel-level cross-view geo-registration aims to align a query image (e.g., drone) to a geo-referenced satellite map so that every query pixel can be ma...
arXiv:2608.29153v1 Announce Type: new Abstract: Automated radiological report generation can alleviate clinical workloads and eliminate observer variability. However, standard free-text generation mo...
arXiv:2608.29211v1 Announce Type: new Abstract: Ground image localization with respect to satellite imagery is a key enabler for metrically-accurate, geo-localized 3D scene reconstruction from uncons...
arXiv:2608.29467v1 Announce Type: new Abstract: Zero-shot anomaly detection (ZSAD) has gained significant attention for its practical value in industrial inspection. Recently, CLIP-based approaches h...
arXiv:2608.29980v1 Announce Type: new Abstract: Unsupervised action segmentation is a challenging task. It involves finding action categories and boundaries in videos without labels. Existing Optimal...
arXiv:2608.30003v1 Announce Type: new Abstract: Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burden...
arXiv:2608.30194v1 Announce Type: new Abstract: Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attr...
arXiv:2608.30450v1 Announce Type: new Abstract: Video virtual try-on aims to transfer a target garment onto a moving person across video frames. Current methods rely on human parsing masks or pose ke...
arXiv:2608.30451v1 Announce Type: new Abstract: Image-based 3D visual grounding is critical for embodied agents, yet existing benchmarks suffer from loose text-observation alignment and neglect tempo...
arXiv:2608.30617v1 Announce Type: new Abstract: Reconstructing editable Computer-Aided Design (CAD) models from images is essential for downstream modification, manufacturing, and design reuse. Howev...
arXiv:2608.30656v1 Announce Type: new Abstract: Proactive tamper localization embeds an imperceptible signal into an image prior to distribution, enabling pixel-level manipulation detection. Existing...
arXiv:2608.30688v1 Announce Type: new Abstract: While face recognition systems are widely deployed, ensuring their demographic reliability and robustness under uncontrolled visual conditions remains...
arXiv:2608.30839v1 Announce Type: new Abstract: Thermal Infrared detection is widely used in autonomous driving, medical AI, etc., but its security has only attracted attention recently. We propose i...
arXiv:2608.31065v1 Announce Type: new Abstract: Surgical phase recognition is key to context-aware computer-assisted feedback in vitreoretinal procedures, yet the scarcity of synchronized multimodal...
arXiv:2608.28794v1 Announce Type: cross Abstract: Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs...