We study a class of multi-stage stochastic programs, which incorporate modeling features from Markov decision processes (MDPs). This class includes structured MDPs with continuous state and action spaces. We extend policy graphs to include decision-dependent uncertainty for one-step transition probabilities as well as a limited form of statistical learning. We focus on the expressiveness of our modeling approach, illustrating ideas with a series of examples of increasing complexity. As a solution method, we develop new variants of stochastic dual dynamic programming, including approximations to handle non-convexities.

As Generative AI (GenAI) systems see growing adoption, a key concern involves the external validity of evaluations, or the extent to which they generalize from lab-based to real-world deployment conditions. Threats to the external validity of GenAI evaluations arise when the source sample of human raters and system outputs used to obtain a system quality estimate differs from the target distribution at deployment time. In this work, we propose a doubly-robust estimation framework designed to address this evaluation sampling bias. Key to our approach is the use of "persona" ratings produced by prompting an LLM evaluator (i.e., an LLM-as-a-judge) to behave as a human rater with specific sociodemographic characteristics. Our doubly-robust framework combines these informative yet imperfect persona ratings with human ratings obtained under evaluation sampling bias to produce statistically valid system quality estimates. In particular, we show that our approach yields valid system quality estimates when either (i) a model trained to predict human ratings using persona ratings and source data observed under sampling bias, or (ii) a reweighting model that corrects for sampling bias is of sufficient quality. We validate our framework theoretically and via a novel Persona Simulation Framework (PSF) designed to systematically manipulate persona quality and the degree of evaluation sampling bias present in source data. Our work provides a principled foundation for combining imperfect persona ratings with human ratings observed under sampling bias to obtain valid system quality estimates.

One-step generators distilled from Masked Diffusion Models (MDMs) compress multiple sampling steps into a single forward pass, enabling efficient text and image synthesis. However, they suffer two key limitations: they inherit modeling bias from the teacher, and their discrete token outputs block gradient flow, preventing post-distillation refinements such as adversarial training, reward-based fine-tuning, and Test-Time Embedding Optimization (TTEO). In this work, we introduce soft embeddings, a simple relaxation that replaces discrete tokens with the expected embeddings under the generator's output distribution. Soft embeddings preserve representation fidelity for one-step discrete generator while providing a fully differentiable continuous surrogate that is compatible with teacher backbones and tokenizer decoders. Integrating soft embeddings into the Di[M]O distillation framework (denoted Soft-Di[M]O) makes one-step generators end-to-end trainable and enables straightforward application of GAN-based refinement, differentiable reward fine-tuning, and TTEO. Empirically, across multiple MDM teachers (e.g., MaskBit, MaskGen), Soft-Di[M]O achieves state-of-the-art one-step results: improved class-to-image performance, a one-step FID of 1.56 on ImageNet-256 with GAN-based refinement, along with higher GenEval and HPS scores on text-to-image with reward fine-tuning, and further gains from TTEO.

Conformal Prediction (CP) is a widely used technique for quantifying uncertainty in machine learning models. In its standard form, CP offers probabilistic guarantees on the coverage of the true label, but it is agnostic to sensitive attributes in the dataset. Several recent works have sought to incorporate fairness into CP by ensuring conditional coverage guarantees across different subgroups. One such method is Conformal Fairness (CF). In this work, we extend the CF framework to the Federated Learning setting and discuss how we can audit a federated model for fairness by analyzing the fairness-related gaps for different demographic groups. Ensuring model fairness is a critical thrust of trustworthy machine learning (ML). ML models, when not calibrated for fairness, are prone to developing biases at each stage of an ML pipeline, as reflected by their predictions Mehrabi et al. (2021). We define bias as disparate performance (i.e., accuracy for classification) between different sub-populations. In the data collection phase, measurement bias may occur due to disproportionate data collection on sub-populations, while representation bias manifests from a lack of training data on specific strata. During training, these biases are inductively learned by the model-leading to incorrect predictions in safety-critical tasks. These models are also susceptible to algorithmic bias, resulting from regularization and optimization techniques during model training, which incorrectly generalize for marginal-ized groups. To mitigate these risks, many ML models must adhere to regulations placed by local governing bodies (Hirsch et al., 2023). Towards model compliance, Komala et al. (2024); Agrawal et al. (2024); Jones et al. (2025) have proposed approaches to enhance model fairness in varying tasks, including federated graph learning and representation learning.

This paper presents Extract-0, a 7-billion parameter language model specifically optimized for document information extraction that achieves performance exceeding models with parameter counts several orders of magnitude larger. Through a novel combination of synthetic data generation, supervised fine-tuning with Low-Rank Adaptation (LoRA), and reinforcement learning via Group Relative Policy Optimization (GRPO), Extract-0 achieves a mean reward of 0.573 on a benchmark of 1,000 diverse document extraction tasks, outperforming GPT-4.1 (0.457), o3 (0.464), and GPT-4.1-2025 (0.459). The training methodology employs a memory-preserving synthetic data generation pipeline that produces 280,128 training examples from diverse document sources, followed by parameterefficient fine-tuning that modifies only 0.53% of model weights (40.4M out of 7.66B parameters). The reinforcement learning phase introduces a novel semantic similarity-based reward function that handles the inherent ambiguity in information extraction tasks. This research demonstrates that task-specific optimization can yield models that surpass general-purpose systems while requiring substantially fewer computational resource.

Large Language Models (LLMs) demonstrate impressive mathematical reasoning abilities, but their solutions frequently contain errors that cannot be automatically verified. Formal theorem proving systems such as Lean 4 offer automated verification with complete accuracy, motivating recent efforts to build specialized prover LLMs that generate verifiable proofs in formal languages. However, a significant gap remains: current prover LLMs solve substantially fewer problems than general-purpose LLMs operating in natural language. We introduce Hilbert, an agentic framework that bridges this gap by combining the complementary strengths of informal reasoning and formal verification. Our system orchestrates four components: an informal LLM that excels at mathematical reasoning, a specialized prover LLM optimized for Lean 4 tactics, a formal verifier, and a semantic theorem retriever. Given a problem that the prover is unable to solve, Hilbert employs recursive decomposition to split the problem into subgoals that it solves with the prover or reasoner LLM. It leverages verifier feedback to refine incorrect proofs as necessary. Experimental results demonstrate that Hilbert substantially outperforms existing approaches on key benchmarks, achieving 99.2% on miniF2F, 6.6% points above the best publicly available method. Hilbert achieves the best known result on PutnamBench. It solves 462/660 problems (70.0%), outperforming proprietary approaches like SeedProver (50.4%) and achieving a 422% improvement over the best publicly available baseline. Thus, Hilbert effectively narrows the gap between informal reasoning and formal proof generation.

This study presents a structured approach to evaluating vulnerabilities within quantum cryptographic protocols, focusing on the BB84 quantum key distribution method and National Institute of Standards and Technology (NIST) approved quantum-resistant algorithms. By integrating AI-driven red teaming, automated penetration testing, and real-time anomaly detection, the research develops a framework for assessing and mitigating security risks in quantum networks. The findings demonstrate that AI can be effectively used to simulate adversarial attacks, probe weaknesses in cryptographic implementations, and refine security mechanisms through iterative feedback. The use of automated exploit simulations and protocol fuzzing provides a scalable means of identifying latent vulnerabilities, while adversarial machine learning techniques highlight novel attack surfaces within AI-enhanced cryptographic processes. This study offers a comprehensive methodology for strengthening quantum security and provides a foundation for integrating AI-driven cybersecurity practices into the evolving quantum landscape.

Risk assessments for advanced AI systems require evaluating both the models themselves and their deployment contexts. We introduce the Societal Capacity Assessment Framework (SCAF), an indicators-based approach to measuring a society's vulnerability, coping capacity, and adaptive capacity in response to AI-related risks. SCAF adapts established resilience analysis methodologies to AI, enabling organisations to ground risk management in insights about country-level deployment conditions. It can also support stakeholders in identifying opportunities to strengthen societal preparedness for emerging AI capabilities. By bridging disparate literatures and the "context gap" in AI evaluation, SCAF promotes more holistic risk assessment and governance as advanced AI systems proliferate globally.

As increasingly capable large language model (LLM)-based agents are developed, the potential harms caused by misalignment and loss of control grow correspondingly severe. To address these risks, we propose an approach that directly measures and controls the agency of these AI systems. We conceptualize the agency of LLM-based agents as a property independent of intelligence-related measures and consistent with the interdisciplinary literature on the concept of agency. We offer (1) agency as a system property operationalized along the dimensions of preference rigidity, independent operation, and goal persistence, (2) a representation engineering approach to the measurement and control of the agency of an LLM-based agent, and (3) regulatory tools enabled by this approach: mandated testing protocols, domain-specific agency limits, insurance frameworks that price risk based on agency, and agency ceilings to prevent societal-scale risks. We view our approach as a step toward reducing the risks that motivate the ``Scientist AI'' paradigm, while still capturing some of the benefits from limited agentic behavior.

Adversarial attacks in machine learning traditionally focus on global perturbations to input data, yet the potential of localized adversarial noise remains underex-plored. This study systematically evaluates localized adversarial attacks across widely-used methods, including FGSM, PGD, and C&W, to quantify their effectiveness, imperceptibility, and computational efficiency. By introducing a binary mask to constrain noise to specific regions, localized attacks achieve significantly lower mean pixel perturbations, higher Peak Signal-to-Noise Ratios (PSNR), and improved Structural Similarity Index (SSIM) compared to global attacks. However, these benefits come at the cost of increased computational effort and a modest reduction in Attack Success Rate (ASR). Our results highlight that iterative methods, such as PGD and C&W, are more robust to localization constraints than single-step methods like FGSM, maintaining higher ASR and imperceptibility metrics. This work provides a comprehensive analysis of localized adversarial attacks, offering practical insights for advancing attack strategies and designing robust defensive systems.