Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 03453v1 Announce Type: cross Abstract: Inference-time alignment methods, such as Best-of-$N$, offer a flexible alternative to training-based alignment by using reward models to select high-quality responses generated by a reference LLM.
arXiv:2607. 03600v1 Announce Type: cross Abstract: Adversarial robustness in Unsupervised Domain Adaptation (UDA) remains a significant challenge due to noisy pseudo labels and inherent distributional shifts between the clean source and adversarially perturbed target domains.
arXiv:2607. 03135v1 Announce Type: cross Abstract: Maintaining consistency between architectural design and runtime-observed behavior is challenging in long-lived safety-critical firmware.
arXiv:2607. 03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, cloud inference adds latency and privacy risk, and fine-tuned LLM pipelines turn general-purpose models into task-specific classifiers.
arXiv:2607. 03177v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) for recovery in autonomous systems lacks causal understanding and generalizes poorly to novel failure scenarios.
arXiv:2607. 03233v1 Announce Type: cross Abstract: The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intelligence, cybersecurity, and cyber investigation.
arXiv:2607. 03171v1 Announce Type: cross Abstract: Decentralised federated learning, based on peer-to-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacy-preserving, communication-efficient training process with no risk of single-point failure.
arXiv:2607. 04306v1 Announce Type: new Abstract: Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not explicitly control which rank-$r$ weight subspace the adapter occupies.
arXiv:2607. 05277v1 Announce Type: cross Abstract: Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data.
arXiv:2607. 04613v1 Announce Type: new Abstract: Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed.
arXiv:2607. 04528v1 Announce Type: new Abstract: Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees, which actions it can take, which failures are repaired, which states are verified, and which evidence is logged.
arXiv:2607. 04329v1 Announce Type: new Abstract: Large language models increasingly operate in settings where humans are active collaborators rather than passive task providers.
arXiv:2607. 02671v1 Announce Type: cross Abstract: Benign overfitting and double descent have come to shape our understanding of generalization in deep learning, establishing that overfitting is not only compatible with good generalization but can actively benefit it.
arXiv:2607. 04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks.
arXiv:2602. 07341v2 Announce Type: replace Abstract: This paper focuses on the scalable robot learning for manipulation in the dexterous robot arm-hand systems, where the remote human-robot interactions via augmented reality (AR) are established to collect the expert demonstration data for improving efficiency.
arXiv:2607. 03454v1 Announce Type: cross Abstract: In this paper, we propose Adversarial Dynamics Priors (ADP) for perturbation-resilient humanoid locomotion control.
arXiv:2607. 02934v1 Announce Type: cross Abstract: Materials phase diagrams are a core knowledge representation in materials science, encoding temperature,composition, phase stability, and phase transformation pathways, with their full understanding requiring thermodynamic mechanism analysis and scientific reasoning.
arXiv:2509. 15908v3 Announce Type: replace-cross Abstract: Nanoporous materials hold promise for diverse sustainable applications, yet their vast chemical space poses challenges for efficient design.
arXiv:2605. 16103v2 Announce Type: replace Abstract: Q-learning is known to suffer from overestimation bias: because the Bellman update maximizes noisy or imperfect action-value estimates, positive errors can be selected and propagated, causing learned values to exceed the true optimal values.
arXiv:2509. 17255v2 Announce Type: replace-cross Abstract: We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source.