digitado

arXiv:2603.28994v1 Announce Type: new Abstract: Knowledge Distillation (KD) has been widely used to improve the quality of latency sensitive models serving live traffic. However, applying KD in production recommender systems with low traffic is challenging: the limited amount of data restricts the teacher model size, and the cost of training a large dedicated teacher may not be justified. Cross-domain KD offers a cost-effective alternative by leveraging a teacher from a data-rich source domain, but introduces unique technical difficulties, […]

Ver mais

arXiv:2603.28992v1 Announce Type: new Abstract: We study training-free flow matching between two Gaussian mixture models (GMMs) using explicit velocity fields that transport one mixture into the other over time. Our baseline approach constructs component-wise Gaussian paths with affine velocity fields satisfying the continuity equation, which yields to a closed-form surrogate for the pairwise kinetic transport cost. In contrast to the exact Gaussian Wasserstein cost, which relies on matrix square-root computations, the surrogate admits a simple analytic expression derived […]

Ver mais

arXiv:2603.28990v1 Announce Type: new Abstract: How much autonomy can multi-agent LLM systems sustain — and what enables it? We present a 25,000-task computational experiment spanning 8 models, 4–256 agents, and 8 coordination protocols ranging from externally imposed hierarchy to emergent self-organization. We observe that autonomous behavior already emerges in current LLM agents: given minimal structural scaffolding (fixed ordering), agents spontaneously invent specialized roles, voluntarily abstain from tasks outside their competence, and form shallow hierarchies — without any pre-assigned […]

Ver mais

arXiv:2603.28988v1 Announce Type: new Abstract: Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes with supply-chain risks, including compromised dependencies, malicious hub artifacts, unsafe deserialization, forged provenance, and backdoored models. A core gap is that training and release claims (e.g., data and code lineage, build environment, and security scanning results) are rarely cryptographically bound to the artifacts […]

Ver mais

arXiv:2603.28986v1 Announce Type: new Abstract: Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduce Mimosa, an evolving multi-agent framework that automatically synthesizes task-specific multi-agent workflows and iteratively refines them through experimental feedback. Mimosa leverages the Model Context Protocol (MCP) for dynamic tool discovery, generates workflow topologies via a meta-orchestrator, executes subtasks through code-generating agents that […]

Ver mais

arXiv:2603.28985v1 Announce Type: new Abstract: By utilising their adaptive activation functions, Kolmogorov-Arnold Networks (KANs) can be applied in a novel way for the diverse machine learning tasks, including cyber threat detection. KANs substitute conventional linear weights with spline-parametrized univariate functions, which allows them to learn activation patterns dynamically, inspired by the Kolmogorov-Arnold representation theorem. In a network traffic data, we show that KANs perform better than traditional Multi-Layer Perceptrons (MLPs), yielding more accurate results with a significantly less […]

Ver mais

arXiv:2603.28981v1 Announce Type: new Abstract: We develop a hybrid conservative finite-volume / bounded-interval multiwavelet formulation for the deterministic one-dimensional Buckley–Leverett equation. Because Buckley–Leverett transport is a nonlinear hyperbolic conservation law with entropy-admissible shocks, the saturation update is performed by a conservative finite-volume scheme with monotone numerical fluxes, while the evolving state is represented and reconstructed in a bounded-interval multiwavelet basis. This strategy preserves the correct shock-compatible transport mechanism and simultaneously provides a hierarchical multiresolution description of the solution. […]

Ver mais

arXiv:2603.28980v1 Announce Type: new Abstract: The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with vast potential in AR/VR and world modeling. While panoramic images have proven effective for scene initialization, existing approaches suffer from a trade-off between visual fidelity and explorability: autoregressive expansion suffers from context drift, while panoramic video generation is limited to low resolution. We present Stepper, a unified framework for text-driven immersive […]

Ver mais

arXiv:2603.28972v1 Announce Type: new Abstract: The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage risks towards third-party cloud providers. We formalise the “Inseparability Paradigm”: advanced context management intrinsically coincides with privacy management. We propose a local “Privacy Guard” — a holistic contextual observer powered by an on-premise Small Language Model (SLM) — that performs […]

Ver mais

arXiv:2603.28971v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) improves sample efficiency by leveraging learned dynamics models for policy optimization. However, the effectiveness of methods such as actor-critic is often limited by compounding model errors, which degrade long-horizon value estimation. Existing approaches, such as Model-Based Value Expansion (MVE), partially mitigate this issue through multi-step rollouts, but remain sensitive to rollout horizon selection and residual model bias. Motivated by the Pontryagin Maximum Principle (PMP), we propose Hamiltonian Actor-Critic (HAC), […]

Ver mais