Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 05675v1 Announce Type: new Abstract: Continual learning (CL) seeks models that acquire new skills without erasing prior knowledge.
arXiv:2605. 27292v2 Announce Type: replace Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters.
arXiv:2606. 05308v1 Announce Type: new Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set.
arXiv:2606. 06133v1 Announce Type: cross Abstract: TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols.
arXiv:2603. 03955v2 Announce Type: replace Abstract: Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation.
arXiv:2606. 05185v1 Announce Type: cross Abstract: Mass gathering events are associated with critical safety incidents caused by insufficient crowd monitoring and inadequate emergency response coordination.
arXiv:2606. 06335v1 Announce Type: new Abstract: Performance estimation under distribution shift aims to predict how a model behaves on an unlabeled test set whose distribution differs from the training data, a scenario that requires reliable indicators that can faithfully reflect model behavior without ground-truth labels.
arXiv:2605. 08318v2 Announce Type: replace Abstract: We study the problem of \emph{architecture selection} for deep learning models trained to solve partial differential equations (PDEs), asking when transformer-based architectures with learned attention outperform Fourier-domain neural operators.
arXiv:2605. 08253v2 Announce Type: replace Abstract: Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based approaches can suffer from \emph{boundary mismatch} at the flow source or from \emph{high-variance} bootstrapping when current and successor noises are independent.
arXiv:2606. 06011v1 Announce Type: cross Abstract: In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasible actions in cooperative multi-agent tasks.
A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings. However, most demonstrations of this ``conjunctive handicap'' rely on passive observation paradigms with limited evidence, where learners have no control over evidence generation.
Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prior work has shown that large language models can simulate realistic human behaviour by generating agent decisions based on demographic prompts and situational context.
Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal model state and environment context. We study reward-hacking monitors in ReAct-style agents acting in Gameable ALFWorld and WebShop.
We introduce pVR, a topological machine learning framework for alignment-free genomic sequence classification that combines $p$-adic numbers with topological data analysis. Each DNA sequence is encoded along two complementary axes: a $p$-adic distance on $k$-mer prefixes, which captures hierarchical positional structure, and a compositional $L_1$ distance on $k$-mer frequencies, which captures local sequence content.
Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality.
Whether Large Language Models (LLMs) exhibit covert psychological manipulation in complex human-AI interactions has garnered increasing safety concerns. However, existing AI safety benchmarks remain largely restricted to explicit rule compliance and static prompts, failing to capture the dynamic and covert nature of manipulative strategies in multi-turn dialogues.
In this work, we propose an agentic gamification framework for hazard-informed learning of robot safety policies through synthetic scenarios. We model scenario generation as an adversarial game between two agents: a Red Team that explores the space of potential failures by constructing hazardous situations, and a Blue Team that incrementally refines safety policies to prevent them.
We investigate the extent to which the language processing of LLMs resembles human cognitive processes, focusing on a human cognitive bias called the $\textit{neglect-zero effect}$. This effect refers to the human tendency to ignore $\textit{zero-models}$, which are configurations that render a proposition vacuously true by virtue of an empty set.
Metasurfaces enable precise manipulation of electromagnetic waves for applications such as beam steering, sensing, and stealth technology. However, inverse design of metasurfaces with targeted EM responses remains challenging due to the computational expense of iterative full wave simulation driven optimization and the limited conditioning fidelity and diversity of existing generative approaches.