March 2026

arXiv:2603.08810v1 Announce Type: new Abstract: There is an increasing interest in social robots assisting older adults during daily life tasks. In this context, non-verbal cues such as deictic gaze are important in natural communication in human-robot interaction. However, the sensibility to deictic-gaze declines naturally with age and results in a reduction in social perception. Therefore, this work explores the benefits of deictic gaze from social robots assisting older adults during daily life tasks, and how age-related differences may […]

Ver mais

arXiv:2603.08809v1 Announce Type: new Abstract: As 3D Gaussian Splatting becomes the de facto representation for interactive 3D assets, robust yet imperceptible watermarking is critical. We present a representation-native framework that separates where to write from how to preserve quality. A Trio-Experts module operates directly on Gaussian primitives to derive priors for carrier selection, while a Safety and Budget Aware Gate (SBAG) allocates Gaussians to watermark carriers, optimized for bit resilience under perturbation and bitrate budgets, and to visual […]

Ver mais

arXiv:2603.08807v1 Announce Type: new Abstract: We consider a matching problem for time series with values in an arbitrary metric space, with the stretching penalty given by the Hellinger kernel. To optimize this matching, we introduce the Elastic Time Warping algorithm with a cubic computational complexity.

Ver mais

arXiv:2603.08806v1 Announce Type: new Abstract: We present Test-Driven AI Agent Definition (TDAD), a methodology that treats agent prompts as compiled artifacts: engineers provide behavioral specifications, a coding agent converts them into executable tests, and a second coding agent iteratively refines the prompt until tests pass. Deploying tool-using LLM agents in production requires measurable behavioral compliance that current development practices cannot provide. Small prompt changes cause silent regressions, tool misuse goes undetected, and policy violations emerge only after deployment. […]

Ver mais

arXiv:2603.08800v1 Announce Type: new Abstract: Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides strong pixel-level perception yet lacks coarse-grained semantic abstraction, leading to limited multi-granularity reasoning. To address this gap, we propose Granulon, a novel DINOv3-based MLLM with adaptive granularity augmentation. Granulon introduces a text-conditioned granularity Controller that dynamically adjusts the visual abstraction level according to the semantic […]

Ver mais

arXiv:2603.08797v1 Announce Type: new Abstract: Applications in emerging domains such as XR are being built as compound inference systems, where multiple ML models are composed in the form of a task graph to service each request. Serving these compound systems efficiently raises two questions: how to apportion end-to-end latency and accuracy budgets between different tasks in a compound inference system, and how to allocate resources effectively for different models with varying resource requirements. We present JigsawServe, the first […]

Ver mais

arXiv:2603.08772v1 Announce Type: new Abstract: This paper constructs a predictor-corrector technique with orthogonal spline collocation finite element method for simulating a FitzHugh-Nagumo system subject to suitable initial and boundary conditions. The developed computational technique approximates the exact solution in time using variable time steps at the predictor phase and a constant time step at the corrector stage while the orthogonal spline collocation finite element method is employed in the space discretization. The new algorithm presents several advantages: (i) […]

Ver mais

arXiv:2603.08765v1 Announce Type: new Abstract: This paper studies a coupled two-dimensional Navier–Stokes–Cahn–Hilliard phase-field model augmented by a transported auxiliary field, and develops a continuous data assimilation (CDA) framework for recovering its trajectories from coarse-in-space observations. We formulate a nudging-based CDA system for the coupled NSCH–auxiliary-field model, in which coarse measurements are incorporated through a general linear observation operator. The observation mechanism is described abstractly by an interpolant satisfying an $H^{2}$-type approximation property, which is compatible with coarse spatial […]

Ver mais

arXiv:2603.08763v1 Announce Type: new Abstract: A key challenge in lifelong imitation learning (LIL) is enabling agents to acquire new skills from expert demonstrations while retaining prior knowledge. This requires preserving the low-dimensional manifolds and geometric structures that underlie task representations across sequential learning. Existing distillation methods, which rely on L2-norm feature matching in raw feature space, are sensitive to noise and high-dimensional variability, often failing to preserve intrinsic task manifolds. To address this, we introduce SPREAD, a geometry-preserving […]

Ver mais

arXiv:2603.08760v1 Announce Type: new Abstract: This paper contributes to the nascent debate around safety cases for frontier AI systems. Safety cases are structured, defensible arguments that a system is acceptably safe to deploy in a given context. Historically, they have been used in safety-critical industries, such as aerospace, nuclear or automotive. As a result, safety cases for frontier AI have risen in prominence, both in the safety policies of leading frontier developers and in international research agendas proposed […]

Ver mais