Research
Research
Research
Research
7,457+ open-access research outputs.
The black hole no-hair theorem is traditionally derived from the uniqueness theorems of general relativity. We show that a quantitative form follows from unitarity together with the standard semiclass…
A key task in AI practice is to assess potential impacts to prevent harm. Current AI tools assisting AI impact assessment have not been designed or evaluated for collaborative team brainstorming, and …
We investigate spin-induced scalarization of Kerr black holes in an Einstein-scalar-Gauss-Bonnet (EsGB) model that does not admit a linear tachyonic instability of the scalar-free solution. The scalar…
We present a unifying Nearly Asymptotically Invariant Manifold (NAIM) framework for understanding Nesterovs Accelerated Gradient (NAG) method. By lifting the first-order gradient flow into a second-or…
The rapid proliferation of harmful and emotionally damaging content on social media platforms has intensified concerns regarding societal harm. While content moderation efforts primarily focus on dete…
Safety evaluations of large language models (LLMs) typically report binary outcomes such as attack success rate, refusal rate, or harmful/not-harmful response classification. While useful, these can h…
Anthropomorphic language describing artificial intelligence (AI) is widespread in media, policy, and everyday discourse; so too are discussions of AI bad behavior, from hallucinations to inappropriate…
Although asymptotically flat black holes generically lack thermodynamic phase transitions, we show that curvature-induced scalarization of electrically charged black holes in Einstein-Maxwell- Scalar-…
Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through…
AI risk assessment is the primary tool for identifying harms caused by AI systems. These include intersectional harms, which arise from the interaction between identity categories (e.g., class and ski…
Conflict in research teams was a near-ubiquitous phenomenon, with the three top issues being lack of respect or overconfidence, non-collegial behaviour and authorship. Most frequently involved (and pe…
Frontier image generation has moved from artistic synthesis toward synthetic visual evidence. Systems such as GPT Image 2, Nano Banana Pro, Nano Banana 2, Grok Imagine, Qwen Image 2.0 Pro, and Seedrea…
Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations re…
AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to …
Large language models (LLMs) are increasingly used for text generation tasks from everyday use to high-stakes enterprise and government applications, including simulated interviews with asylum seekers…
Despite growing concerns about the risks of Generative AI (GenAI), there is limited understanding of public perceptions of these risks and their associated failure modes -- defined as recurring patter…
The real-world deployment of Vision-Language-Action (VLA) models remains limited by the risk of unpredictable and irreversible physical harm. However, we currently lack effective mechanisms to proacti…
Black holes with resonant hair are static, spherical, electrically charged solutions of the Einstein-Maxwell-(gauged-)scalar system. Scalar self-interactions are mandatory for their existence. Initial…
We establish a thermodynamic-optical duality that directly bridges the semiclassical quantum evaporation of black holes with their classical macroscopic geometry. By employing a diffeomorphic inversio…
Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation app…
Free open-access publishing with Google Scholar indexing.
Submission Guide →