Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.13267v1 Announce Type: new Abstract: Scientific charts encode quantities in axes, legends, and geometric marks, yet large vision-language models still treat them as natural photographs. Vi...
arXiv:2609.13991v1 Announce Type: new Abstract: Reconstructing 3D objects from brain signals offers a promising avenue for understanding human visual cognition. While prior work has shown initial suc...
arXiv:2609.14258v1 Announce Type: new Abstract: Vision-language models (VLMs) remain vulnerable to jailbreaks that distribute harmful intent across text and images, making unimodal safety mechanisms...
arXiv:2609.14469v1 Announce Type: new Abstract: Accurate 3D localization of unmanned aerial vehicles (UAVs) remains challenging for existing multimodal approaches due to sparse LiDAR geometry, modali...
arXiv:2609.14654v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) are typically evaluated using held-out classification accuracy, an approach that presupposes predictions are based...
arXiv:2609.14899v1 Announce Type: new Abstract: Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent...
arXiv:2609.15032v1 Announce Type: new Abstract: Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either r...
arXiv:2609.15150v1 Announce Type: new Abstract: Unpaired cross-modal distillation transfers grade structure from histopathology into a micro-ultrasound (micro-US) encoder by aligning a pooled needle-...
arXiv:2609.13777v1 Announce Type: cross Abstract: Learned components are increasingly integrated into geometric visual--inertial estimators to provide motion, depth, bias, uncertainty, or confidence...
arXiv:2609.14829v1 Announce Type: cross Abstract: We introduce Enemray, a Hassaniya-centric language model that enables general-purpose interaction in Hassaniya. Enemray is trained around a stability...
arXiv:2609.15685v1 Announce Type: cross Abstract: Most knowledge of graphical perception comes from behavioral studies. Understanding from a neural perspective is much more limited due in part to neu...
arXiv:2510.23224v2 Announce Type: replace Abstract: The rapid digitization of histopathology slides has opened new opportunities for computational tools in clinical and research workflows. Content-ba...
The paper introduces a modular correction framework for large language models that uses Activated LoRA adapters and a context-aware routing mechanism to mitigate harmful outputs. By allowing expert adapters to activate mid-sequence without invalidating the KV cache, the system achieves low-latency, targeted correction during generation. Experiments show improved alignment on safety benchmarks while maintaining task performance, presenting a lightweight, scalable approach to safer LLM deployments.
arXiv:2512.15971v2 Announce Type: replace Abstract: Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception u...
arXiv:2609.13499v1 Announce Type: cross Abstract: Private Evolution (PE) generates high-fidelity synthetic data in federated settings without exposing users' raw data. It aggregates clipped user vote...
arXiv:2609.13552v1 Announce Type: new Abstract: Generative AI is increasingly being used informally in Air Traffic Management (ATM) for tasks such as flight plan generation, trajectory interpretation...
arXiv:2609.14422v1 Announce Type: new Abstract: Agentic Network Operations (NetOps) are an emerging paradigm promising to enable workload-aware, self-adjustable, and reliable autonomous networks. Whi...
arXiv:2609.13231v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existing fine-tuning methods provid...
arXiv:2609.13259v1 Announce Type: cross Abstract: Virtual Try-On (VTON) aims to dress a person with the reference garment, producing visually reasonable results aligned with human preferences. Turnin...
arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also in...