Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.32719v1 Announce Type: cross Abstract: Advanced Driver Assistance Systems have become increasingly widespread, aiming to support drivers, reduce workload, and improve traffic safety. Howev...
arXiv:2604.06502v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integra...
arXiv:2605.23420v2 Announce Type: replace Abstract: Social norms reflect shared expectations on acceptable behavior. Measuring social norms alignment remains challenging, with existing approaches typ...
arXiv:2608.01629v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly evaluate human writing in high-stakes domains such as hiring and academic assessment, putting non-native...
arXiv:2610.16318v2 Announce Type: replace Abstract: Large language models (LLMs) can reduce hallucination by abstaining from questions they would likely get wrong. Abstention can be implemented outsi...
arXiv:2610.33135v1 Announce Type: new Abstract: Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with com...
arXiv:2610.34333v1 Announce Type: new Abstract: Language models switch tasks from demonstrations, but vision still often relies on separate systems for restoration, editing, and stylization. A before...
arXiv:2610.35361v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has become a promising representation for real-time novel view synthesis and 3D scene reconstruction. For practical deploy...
arXiv:2610.35756v1 Announce Type: new Abstract: Recent advancements in text-guided 3D editing, particularly with 3D Gaussian Splatting (3DGS), have shown promise but still lag behind the flexibility...
arXiv:2511.22459v3 Announce Type: replace Abstract: We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Captu...
arXiv:2603.12657v2 Announce Type: replace Abstract: Scene-level neural volumetric reconstruction from monocular videos remains challenging, especially under severe domain shifts. Although recent adva...
arXiv:2605.15195v2 Announce Type: replace Abstract: Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also prov...
arXiv:2511.17384v3 Announce Type: replace-cross Abstract: Visual large language models (VLLMs) are increasingly used as embodied agents, yet industrial warehouses demand more than reaching a goal: ag...
arXiv:2610.33644v1 Announce Type: new Abstract: Research ideas are always proposed under resource constraints: a plan must fit the available compute, API credit, and time. Yet evaluations of research...
arXiv:2610.33477v1 Announce Type: cross Abstract: We present a generic actor-critic method that combines a ridge-regularized pathwise least-squares temporal-difference (LSTD) critic with importance-c...
arXiv:2610.34674v1 Announce Type: cross Abstract: Safe household navigation requires robots to regulate clearance and speed according to what an obstacle is and how close it is, without unnecessary c...
arXiv:2610.35391v1 Announce Type: cross Abstract: High-fidelity digital twins in continuous biomanufacturing are often bottlenecked by incomplete kinetic models, while standard data-driven algorithms...
arXiv:2609.34519v2 Announce Type: replace Abstract: On-Policy Self-Distillation (OPSD) has emerged as a promising paradigm for safety alignment, delivering dense, token-level supervision by distillin...
arXiv:2610.26524v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as user simulators, but can they faithfully reproduce an individual's behavior and decision logi...
arXiv:2605.30913v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in conversational settings where user phrasing ranges from polite to casual to toxic,...