Safe Exploration via Policy Priors
arXiv:2601.19612v4 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) env
Knowledge catalogue
arXiv:2601.19612v4 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) env
arXiv:2608.12829v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffus
arXiv:2608.13029v1 Announce Type: cross Abstract: The field of bioinformatics struggles with legacy code - old code that is commonly used but may no longer have a maintainer, or may be written in an n
arXiv:2608.13263v1 Announce Type: new Abstract: Large language model serving faces a critical memory bottleneck: the KV cache grows with sequence length and batch size. PagedAttention uses fixed-size
arXiv:2608.11392v1 Announce Type: cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary.Recent work shows that dropping a stan
arXiv:2608.12037v1 Announce Type: new Abstract: Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust
arXiv:2608.12100v1 Announce Type: cross Abstract: In high-stakes applications, reliable confidence estimates are as important as the predictions themselves. Confidence calibration ensures that predict
arXiv:2608.12304v1 Announce Type: new Abstract: Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural
arXiv:2608.11324v1 Announce Type: cross Abstract: This paper proposes a contextual quality-diversity evolutionary reinforcement-learning controller, CQD-ERL, for the supervisory control of a tropical,
arXiv:2608.12051v1 Announce Type: new Abstract: Aggregate metrics may not fully reflect performance in insufficiently examined high-risk driving conditions. We propose RISC (Risk-Informed Slice Covera
arXiv:2608.12083v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) achieve strong predictive performance on graph-structured data across domains such as chemistry, biology, and network ana
arXiv:2608.11227v1 Announce Type: new Abstract: Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retr
arXiv:2608.11787v1 Announce Type: cross Abstract: Generating actionable financial advice from business records demands that models integrate numerical reasoning, domain knowledge, and sound judgment,
arXiv:2608.11658v1 Announce Type: cross Abstract: Many reinforcement learning systems, from fleet management to traffic signal control, must serve an objective that changes dynamically after deploymen
arXiv:2606.13840v2 Announce Type: replace-cross Abstract: Autonomous driving is shifting from isolated vehicle intelligence toward multi-agent embodied systems that share perception, infer intent, and
arXiv:2507.22423v3 Announce Type: replace Abstract: To engineer AGI, we should first capture the essence of intelligence in a species-agnostic form that can be evaluated, while being sufficiently gene
arXiv:2608.11951v1 Announce Type: cross Abstract: Extreme events in air transport, such as severe arrival delays and abnormal air times, cause cascading network disruptions with substantial operationa
arXiv:2608.11607v1 Announce Type: new Abstract: Accurate foreground masks can still form an incorrect surgical-instrument instance set: duplicate, fragmented, merged, missed, or empty-frame prediction
arXiv:2608.11410v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers considerable promise for optimizing ICU treatment decisions, yet standard evaluation metrics Mean Squared Err
arXiv:2608.10203v1 Announce Type: new Abstract: Despite the success of convolutional neural networks in image classification tasks and their general application in multi-modal models, their susceptibi
arXiv:2608.10367v1 Announce Type: new Abstract: Direct teleoperation of vehicles faces critical technical bottlenecks: communication latency and the operator's inability to physically perceive unmodel
arXiv:2608.10885v1 Announce Type: new Abstract: Pulmonary nodule malignancy prediction typically depends on image-trained specialist deep learning (DL) models that require substantial annotated imagin
arXiv:2608.11025v1 Announce Type: new Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leadi
arXiv:2608.10386v1 Announce Type: new Abstract: Sample-efficient reinforcement learning for autonomous driving is often limited by the trade-off between data efficiency and model bias. While world mod
arXiv:2509.26087v5 Announce Type: replace Abstract: In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable roa
arXiv:2608.10339v1 Announce Type: cross Abstract: Hospital quality improvement (QI) programs routinely face multiple candidate interventions to optimize hospital flow, but existing methods struggle to
arXiv:2608.11171v1 Announce Type: cross Abstract: The Workshop on Trustworthy Natural Language Processing (TrustNLP), co-located with major ACL conferences since 2021, has grown from 8 proceedings pap
arXiv:2602.09924v4 Announce Type: replace-cross Abstract: Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains c
arXiv:2608.10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interact
arXiv:2608.10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff. Deduplication filters, seman
arXiv:2608.10730v1 Announce Type: cross Abstract: The pursuit of artificial general intelligence (AGI) rests on a seemingly self-evident premise: that general intelligence, the kind of flexible, domai
arXiv:2608.10327v1 Announce Type: new Abstract: Can AI systems be aligned to human values? The popularization of large language models (LLMs) and multi-modal foundation models has seen a rise in harms
arXiv:2607.17188v2 Announce Type: replace Abstract: While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can
arXiv:2608.10903v1 Announce Type: new Abstract: Reliable clinical deployment of machine learning requires models that know when they are likely to fail, particularly for subgroups underrepresented in
arXiv:2608.08158v1 Announce Type: new Abstract: Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning. Reward shaping addresses these limitations
arXiv:2608.09622v1 Announce Type: new Abstract: Reliability qualification of advanced semiconductor devices requires sequential stress decisions that balance characterization objectives against multip
arXiv:2608.09857v1 Announce Type: cross Abstract: Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of such systems has largely focused on
arXiv:2608.09246v1 Announce Type: new Abstract: Industrial processes are complex systems composed of multiple interacting sensors that generate multivariate time series (MTS). Detecting anomalies in s
arXiv:2301.07210v5 Announce Type: replace-cross Abstract: Digital twins are simulation-based models designed to predict how a real-world process will evolve in response to interventions. This modellin
arXiv:2608.09025v1 Announce Type: new Abstract: Financial agents can turn correct context into an unauthorized effect: a customer-facing commitment, trade, or deployed policy. We present SAGE-Fin, a f
arXiv:2608.07965v1 Announce Type: new Abstract: Gamification is especially effective in learning domains requiring active problem-solving and iterative skill-building, such as cybersecurity education.
arXiv:2608.09333v1 Announce Type: new Abstract: Large-scale language models for autonomous driving enable enhanced global understanding and long-horizon planning. However, when deployed in isolated ve
arXiv:2608.09011v1 Announce Type: new Abstract: Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Mode
arXiv:2608.07520v1 Announce Type: cross Abstract: Mass religious gatherings such as the Kumbh Mela concentrate tens of millions of people into a single region over a few weeks, producing intense, repe
arXiv:2608.08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large L
arXiv:2404.03082v3 Announce Type: replace Abstract: Partially ordered sets (posets) are discrete mathematical structures that formalize the notion of comparison without forcing every pair of objects t
arXiv:2608.09547v1 Announce Type: new Abstract: Autonomous Unmanned Aerial Vehicles (UAVs) are complex cyber-physical systems that require the coordinated integration of flight control, navigation, pe
arXiv:2608.08199v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in group decision-making with other LLMs and humans. Yet it remains unclear whether their influen
arXiv:2506.07223v2 Announce Type: replace Abstract: Large language models (LLMs) have substantially improved the planning capabilities of embodied agents, enabling their deployment in dynamic and safe
arXiv:2608.09658v1 Announce Type: cross Abstract: Human-Robot Collaboration (HRC) plays a vital role in dynamic, high mix, low volume industrial scenarios such as remanufacturing, which frequently fac
arXiv:2608.07945v1 Announce Type: cross Abstract: Cloud-native serverless data warehouses achieve fine-grained elasticity by decoupling storage from compute, yet determining the optimal resource alloc
arXiv:2608.09278v1 Announce Type: cross Abstract: GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications. However, this growth has outpaced the maturity
arXiv:2608.08200v1 Announce Type: new Abstract: Communication delay remains a central challenge in telerobotics, where it disrupts visuomotor coordination and reduces task precision. Motion scaling is
arXiv:2509.23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because
arXiv:2608.09098v1 Announce Type: new Abstract: End-to-end planning has shown strong promise for autonomous driving, but most existing methods are designed for structured urban roads and generalize po
arXiv:2608.06940v1 Announce Type: new Abstract: LLM judge panels are a standard evaluation tool, but prior work reports highly correlated panel errors: nine judges provide roughly the effective inform
arXiv:2608.06674v1 Announce Type: new Abstract: Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in
arXiv:2602.20860v2 Announce Type: replace Abstract: While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect n
arXiv:2608.06939v1 Announce Type: new Abstract: Adverse weather causes diverse and complex image degradations, severely compromising the reliability of computer vision systems. Existing all-in-one res
arXiv:2608.06876v1 Announce Type: cross Abstract: In the era of Industrial Internet of Things (IIoT) and Cyber-Physical Systems (CPS), Federated Learning (FL) offers a promising decentralized intellig