March 2026

arXiv:2603.15802v1 Announce Type: new Abstract: In many time series forecasting settings, the target time series is accompanied by exogenous covariates, such as promotions and prices in retail demand; temperature in energy load; calendar and holiday indicators for traffic or sales; and grid load or fuel costs in electricity pricing. Ignoring these exogenous signals can substantially degrade forecasting accuracy, particularly when they drive spikes, discontinuities, or regime and phase changes in the target series. Most current time series foundation […]

Ver mais

arXiv:2603.15800v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on jailbreak defenses that detect and refuse explicitly unsafe inputs, such approaches often overlook contextual safety, which requires models to distinguish subtle contextual differences between scenarios that may appear similar but diverge significantly in safety intent. In this work, we present […]

Ver mais

arXiv:2603.15799v1 Announce Type: new Abstract: Prose2Policy (P2P) is a LLM-based practical tool that translates natural-language access control policies (NLACPs) into executable Rego code (the policy language of Open Policy Agent, OPA). It provides a modular, end-to-end pipeline that performs policy detection, component extraction, schema validation, linting, compilation, automatic test generation and execution. Prose2Policy is designed to bridge the gap between human-readable access requirements and machine-enforceable policy-as-code (PaC) while emphasizing deployment reliability and auditability. We evaluated Prose2Policy on the […]

Ver mais

arXiv:2603.15798v1 Announce Type: new Abstract: The proliferation of agent benchmarks has created critical fragmentation that threatens research productivity. Each new benchmark requires substantial custom integration, creating an “integration tax” that limits comprehensive evaluation. We propose CUBE (Common Unified Benchmark Environments), a universal protocol standard built on MCP and Gym that allows benchmarks to be wrapped once and used everywhere. By separating task, benchmark, package, and registry concerns into distinct API layers, CUBE enables any compliant platform to access […]

Ver mais

arXiv:2603.15797v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous spatiotemporal dynamics governed by Partial Differential Equations (PDEs), often resulting in non-physical hallucinations. Existing approaches typically resort to costly, domain-specific fine-tuning, which severely limits cross-domain generalization and interpretability. To bridge this gap, we propose OMNIFLOW, a neuro-symbolic architecture designed to ground frozen multimodal LLMs in fundamental physical laws without requiring domain-specific parameter updates. OMNIFLOW introduces a novel […]

Ver mais

arXiv:2603.15796v1 Announce Type: new Abstract: End-to-end (e2e) latency in head-mounted displays (HMD) is the time delay between a physical change in the world (e.g., a user’s head movement) and the moment the display updates to reflect that change. Tracking, rendering, and other computation in real systems invariably introduce some amount of e2e latency to all HMDs. In modern devices this latency is usually in the range of 12-60 milliseconds which is partially addressed through pose prediction and late […]

Ver mais

arXiv:2603.15789v1 Announce Type: new Abstract: Reinforcement learning in massively parallel physics simulations has driven major progress in sim-to-real robot learning. However, current approaches remain brittle and task-specific, relying on extensive per-task engineering to design rewards, curricula, and demonstrations. Even with this engineering, they often fail on long-horizon, contact-rich manipulation tasks and do not meaningfully scale with compute, as performance quickly saturates when training revisits the same narrow regions of state space. We introduce Method, a simple and scalable […]

Ver mais

arXiv:2603.15783v1 Announce Type: new Abstract: This paper introduces a novel multi-objective integrated sensing and communications (ISAC) framework to enable collaborative wireless sensing in conjunction with over-the-air federated-edge learning (OTA-FEEL). The framework enables multi-task OTA aggregation to handle sensing and learning simultaneously, while benefiting from dual-purpose uplink signals for both communications and target sensing. Starting from characterizing the local sufficient statistics at each edge device and establishing its stationary, we develop a tractable analytical expression for the local sufficient […]

Ver mais

arXiv:2603.15782v1 Announce Type: new Abstract: We present a family of fast pseudo-approximation algorithms for the minimum balanced vertex separator problem in a graph. Given a graph $G=(V,E)$ with $n$ vertices and $m$ edges, and a (constant) balance parameter $cin(0,1/2)$, where $G$ has some (unknown) $c$-balanced vertex separator of size ${rm OPT}_c$, we give a (Monte-Carlo randomized) algorithm running in $O(n^{O(varepsilon)}m^{1+o(1)})$ time that produces a $Theta(1)$-balanced vertex separator of size $O({rm OPT}_ccdotsqrt{(log n)/varepsilon})$ for any value $varepsilonin[Theta(1/log(n)),Theta(1)]$. In particular, […]

Ver mais

arXiv:2603.15780v1 Announce Type: new Abstract: Machine learning has been progressively generalised to operate within non-Euclidean domains, but geometrically accurate methods for learning on surfaces are still falling behind. The lack of closed-form Riemannian operators, the non-differentiability of their discrete counterparts, and poor parallelisation capabilities have been the main obstacles to the development of the field on meshes. A principled framework to compute the exponential map on Riemannian surfaces discretised as meshes is straightest geodesics, which also allows to […]

Ver mais