Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety requirements. In real deployments, providers distribute a global model to many edge devices, where each client personalizes the model using private data. When a deletion request is issued, clients may ignore it or falsely claim compliance, and providers cannot check their parameters or data. This makes verification difficult, especially because personalized models must forget the targeted samples while preserving local utility, and verification must remain lightweight on edge devices. We introduce ZK APEX, a zero-shot personalized unlearning method that operates directly on the personalized model without retraining. ZK APEX combines sparse masking on the provider side with a small Group OBS compensation step on the client side, using a blockwise empirical Fisher matrix to create a curvature-aware update designed for low overhead. Paired with Halo2 zero-knowledge proofs, it enables the provider to verify that the correct unlearning transformation was applied without revealing any private data or personalized parameters. On Vision Transformer classification tasks, ZK APEX recovers nearly all personalization accuracy while effectively removing the targeted information. Applied to the OPT125M generative model trained on code data, it recovers around seventy percent of the original accuracy. Proof generation for the ViT case completes in about two hours, more than ten million times faster than retraining-based checks, with less than one gigabyte of memory use and proof sizes around four hundred megabytes. These results show the first practical framework for verifiable personalized unlearning on edge devices.

The latency and power consumption of large language models (LLMs) are major constraints when serving them across a wide spectrum of hardware platforms, from mobile edge devices to cloud GPU clusters. Benchmarking is crucial for optimizing efficiency in both model deployment and next-generation model development. To address this need, we open-source a simple profiling tool, \textbf{ELANA}, for evaluating LLMs. ELANA is designed as a lightweight, academic-friendly profiler for analyzing model size, key-value (KV) cache size, prefilling latency (Time-to-first-token, TTFT), generation latency (Time-per-output-token, TPOT), and end-to-end latency (Time-to-last-token, TTLT) of LLMs on both multi-GPU and edge GPU platforms. It supports all publicly available models on Hugging Face and offers a simple command-line interface, along with optional energy consumption logging. Moreover, ELANA is fully compatible with popular Hugging Face APIs and can be easily customized or adapted to compressed or low bit-width models, making it ideal for research on efficient LLMs or for small-scale proof-of-concept studies. We release the ELANA profiling tool at: https://github.com/enyac-group/Elana.

Reinsurance decision-making exhibits the core structural properties that motivate multi-agent models: distributed and asymmetric information, partial observability, heterogeneous epistemic responsibilities, simulator-driven environment dynamics, and binding prudential and regulatory constraints. Deterministic workflow automation cannot meet these requirements, as it lacks the epistemic flexibility, cooperative coordination mechanisms, and norm-sensitive behaviour required for institutional risk-transfer. We propose the Reinsurance Constrained Multi-Agent Simulation Process (R-CMASP), a formal model that extends stochastic games and Dec-POMDPs by adding three missing elements: (i) simulator-coupled transition dynamics grounded in catastrophe, capital, and portfolio engines; (ii) role-specialized agents with structured observability, belief updates, and typed communication; and (iii) a normative feasibility layer encoding solvency, regulatory, and organizational rules as admissibility constraints on joint actions. Using LLM-based agents with tool access and typed message protocols, we show in a domain-calibrated synthetic environment that governed multi-agent coordination yields more stable, coherent, and norm-adherent behaviour than deterministic automation or monolithic LLM baselines--reducing pricing variance, improving capital efficiency, and increasing clause-interpretation accuracy. Embedding prudential norms as admissibility constraints and structuring communication into typed acts measurably enhances equilibrium stability. Overall, the results suggest that regulated, simulator-driven decision environments are most naturally modelled as norm-governed, simulator-coupled multi-agent systems.

Abstract--Short-term voltage stability assessment (STVSA) is critical for secure power system operation. While classical machine learning-based methods have demonstrated strong performance, they still face challenges in robustness under adversarial conditions. This paper proposes QST Aformer--a tailored quantum-enhanced Transformer architecture that embeds parameterized quantum circuits (PQCs) into attention mechanisms--for robust and efficient STVSA. A dedicated adversarial training strategy is developed to defend against both white-box and gray-box attacks. Furthermore, diverse PQC architectures are benchmarked to explore trade-offs between expressiveness, convergence, and efficiency. T o the best of our knowledge, this is the first work to systematically investigate the adversarial vulnerability of quantum machine learning-based STVSA. Case studies on the IEEE 39-bus system demonstrate that QST Aformer achieves competitive accuracy, reduced complexity, and stronger robustness, underscoring its potential for secure and scalable STVSA under adversarial conditions. ITH the high penetration of converter-interfaced renewable energy sources and the growing deployment of fast-acting power electronic devices, maintaining short-term voltage stability (STVS) in modern power systems has become a pressing challenge [1]. STVS characterizes a power system's ability to preserve acceptable voltage profiles during the initial seconds following a disturbance [2], and this stability is primarily influenced by the dynamic behavior of fast acting loads, Li is with the School of Electrical Engineering, Northeast Electric Power University, Jilin 132012, China (e-mail: liyang@neepu.edu.cn). C. Ma is with State Grid Shandong Electric Power Company Jiaozhou Power Supply Company, Jiaozhou 266300, China (email:machong58112233@163.com). Z. Li is with the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China (email: Y uanzheng Li@hust.edu.cn). Sen Li is with the Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong.

Fact-checking health-related claims has become increasingly critical as misinformation proliferates online. Effective verification requires both the retrieval of high-quality evidence and rigorous reasoning processes. In this paper, we propose a two-stage framework for health misinformation detection: Agreement Score Prediction followed by Multi-Agent Debate. In the first stage, we employ large language models (LLMs) to independently evaluate retrieved articles and compute an aggregated agreement score that reflects the overall evidence stance. When this score indicates insufficient consensus-falling below a predefined threshold-the system proceeds to a second stage. Multiple agents engage in structured debate to synthesize conflicting evidence and generate well-reasoned verdicts with explicit justifications. Experimental results demonstrate that our two-stage approach achieves superior performance compared to baseline methods, highlighting the value of combining automated scoring with collaborative reasoning for complex verification tasks.

Learning is most effective when it's connected to relevant, relatable examples that resonate with learners on a personal level. However, existing educational AI tools don't focus on generating examples or adapting to learners' changing understanding, struggles, or growing skills. We've developed ExaCraft, an AI system that generates personalized examples by adapting to the learner's dynamic context. Through the Google Gemini AI and Python Flask API, accessible via a Chrome extension, ExaCraft combines user-defined profiles (including location, education, profession, and complexity preferences) with real-time analysis of learner behavior. This ensures examples are both culturally relevant and tailored to individual learning needs. The system's core innovation is its ability to adapt to five key aspects of the learning context: indicators of struggle, mastery patterns, topic progression history, session boundaries, and learning progression signals. Our demonstration will show how ExaCraft's examples evolve from basic concepts to advanced technical implementations, responding to topic repetition, regeneration requests, and topic progression patterns in different use cases.

Learning fast and robust ball-kicking skills is a critical capability for humanoid soccer robots, yet it remains a challenging problem due to the need for rapid leg swings, postural stability on a single support foot, and robustness under noisy sensory input and external perturbations (e.g., opponents). This paper presents a reinforcement learning (RL)-based system that enables humanoid robots to execute robust continual ball-kicking with adaptability to different ball-goal configurations. The system extends a typical teacher-student training framework -- in which a "teacher" policy is trained with ground truth state information and the "student" learns to mimic it with noisy, imperfect sensing -- by including four training stages: (1) long-distance ball chasing (teacher); (2) directional kicking (teacher); (3) teacher policy distillation (student); and (4) student adaptation and refinement (student). Key design elements -- including tailored reward functions, realistic noise modeling, and online constrained RL for adaptation and refinement -- are critical for closing the sim-to-real gap and sustaining performance under perceptual uncertainty. Extensive evaluations in both simulation and on a real robot demonstrate strong kicking accuracy and goal-scoring success across diverse ball-goal configurations. Ablation studies further highlight the necessity of the constrained RL, noise modeling, and the adaptation stage. This work presents a system for learning robust continual humanoid ball-kicking under imperfect perception, establishing a benchmark task for visuomotor skill learning in humanoid whole-body control.

Estimating catastrophic harms from frontier AI is hindered by deep ambiguity: many of its risks are not only unobserved but unanticipated by analysts. The central limitation of current risk analysis is the inability to populate the $\textit{catastrophic event space}$, or the set of potential large-scale harms to which probabilities might be assigned. This intractability is worsened by the $\textit{Lucretius problem}$, or the tendency to infer future risks only from past experience. We propose a process of $\textit{dark speculation}$, in which systematically generating and refining catastrophic scenarios ("qualitative" work) is coupled with estimating their likelihoods and associated damages (quantitative underwriting analysis). The idea is neither to predict the future nor to enable insurance for its own sake, but to use narrative and underwriting tools together to generate probability distributions over outcomes. We formalize this process using a simplified catastrophic Lévy stochastic framework and propose an iterative institutional design in which (1) speculation (including scenario planning) generates detailed catastrophic event narratives, (2) insurance underwriters assign probabilistic and financial parameters to these narratives, and (3) decision-makers synthesize the results into summary statistics to inform judgment. Analysis of the model reveals the value of (a) maintaining independence between speculation and underwriting, (b) analyzing multiple risk categories in parallel, and (c) generating "thick" catastrophic narrative rich in causal (counterfactual) and mitigative detail. While the approach cannot eliminate deep ambiguity, it offers a systematic approach to reason about extreme, low-probability events in frontier AI, tempering complacency and overreaction. The framework is adaptable for iterative use and can be further augmented with AI systems.

As large AI models become increasingly valuable assets, the risk of model weight exfiltration from inference servers grows accordingly. An attacker controlling an inference server may exfiltrate model weights by hiding them within ordinary model outputs, a strategy known as steganography. This work investigates how to verify model responses to defend against such attacks and, more broadly, to detect anomalous or buggy behavior during inference. We formalize model exfiltration as a security game, propose a verification framework that can provably mitigate steganographic exfiltration, and specify the trust assumptions associated with our scheme. To enable verification, we characterize valid sources of non-determinism in large language model inference and introduce two practical estimators for them. We evaluate our detection framework on several open-weight models ranging from 3B to 30B parameters. On MOE-Qwen-30B, our detector reduces exfiltratable information to <0.5% with false-positive rate of 0.01%, corresponding to a >200x slowdown for adversaries. Overall, this work further establishes a foundation for defending against model weight exfiltration and demonstrates that strong protection can be achieved with minimal additional cost to inference providers.

The proliferation of probabilistic AI has prompted proposals for specialized stochastic computers. Despite promising efficiency gains, these proposals have failed to gain traction because they rely on fundamentally limited modeling techniques and exotic, unscalable hardware. In this work, we address these shortcomings by proposing an all-transistor probabilistic computer that implements powerful denoising models at the hardware level. A system-level analysis indicates that devices based on our architecture could achieve performance parity with GPUs on a simple image benchmark using approximately 10,000 times less energy.