digitado

arXiv:2603.22750v1 Announce Type: new Abstract: Active learning reduces labeling costs by selecting samples that maximize information gain. A dominant framework, Query-by-Committee (QBC), typically relies on perturbation-based diversity by inducing model disagreement through random feature subsetting or data blinding. While this approximates one notion of epistemic uncertainty, it sacrifices direct characterization of the plausible hypothesis space. We propose the complementary approach: Rashomon Ensembled Active Learning (REAL) which constructs a committee by exhaustively enumerating the Rashomon Set of all near-optimal […]

Ver mais

arXiv:2603.22644v1 Announce Type: new Abstract: We consider a PAC-Bayes type learning rule for binary classification, balancing the training error of a randomized ”posterior” predictor with its KL divergence to a pre-specified ”prior”. This can be seen as an extension of a modified two-part-code Minimum Description Length (MDL) learning rule, to continuous priors and randomized predictions. With a balancing parameter of $lambda=1$ this learning rule recovers an (empirical) Bayes posterior and a modified variant recovers the profile posterior, linking […]

Ver mais

arXiv:2603.22563v1 Announce Type: new Abstract: Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differentially private pipeline that is well suited to the distinct structure of reinforcement learning from human feedback. We propose a privacy-preserving framework that imposes differential privacy only on reward learning and derives the final policy from the resulting private reward model. […]

Ver mais

arXiv:2603.22468v1 Announce Type: new Abstract: We derive posterior contraction rates (PCRs) and finite-sample Bernstein von Mises (BvM) results for non-parametric Bayesian models by extending the diffusion-based framework of Mou et al. (2024) to the infinite-dimensional setting. The posterior is represented as the invariant measure of a Langevin stochastic partial differential equation (SPDE) on a separable Hilbert space, which allows us to control posterior moments and obtain non-asymptotic concentration rates in Hilbert norms under various likelihood curvature and regularity […]

Ver mais

arXiv:2603.22355v1 Announce Type: new Abstract: Knowledge distillation has emerged as a powerful technique for compressing large language models (LLMs) into efficient, deployable architectures while preserving their advanced capabilities. Recent advances in low-rank knowledge distillation, particularly methods like Low-Rank Clone (LRC), have demonstrated remarkable empirical success, achieving comparable performance to full-parameter distillation with significantly reduced training data and computational overhead. However, the theoretical foundations underlying these methods remain poorly understood. In this paper, we establish a rigorous theoretical framework […]

Ver mais

arXiv:2603.22488v1 Announce Type: new Abstract: Current architecture proposals within standards development organizations such as ETSI and 3GPP enable sensing capabilities in mobile networks; however, they do not include a repository for storing sensing data. Such a repository can be used for AI model training and to complement ongoing sensing service provisioning by improving efficiency and accuracy. One way of realizing this is through the fusion of historical sensing data with live sensing data. In this paper, we study […]

Ver mais

arXiv:2603.22480v1 Announce Type: new Abstract: Serverless computing is a cloud execution model where developers run code, and the server management is handled by the cloud provider. Serverless computing is increasingly gaining popularity as more systems adopt it to enhance scalability and reduce operational costs. While it has numerous benefits, it also embodies unique challenges inherent to serverless computing. One such challenge is Technical Debt (TD), which is exacerbated by the complexities of the serverless paradigm. While prior work […]

Ver mais

arXiv:2603.22474v1 Announce Type: new Abstract: Software analytics often builds from labeled data. Labeling can be slow, error prone, and expensive. When human expertise is scarce, SE researchers sometimes ask large language models (LLMs) for the missing labels. While this has been successful in some domains, recent results show that LLM-based labeling has blind spots. Specifically, their labeling is not effective for higher dimensional multi-objective problems. To address this task, we propose a novel LLM prompting strategy called SynthCore. […]

Ver mais

arXiv:2603.22473v1 Announce Type: new Abstract: Hybrid language models combining attention with state space models (SSMs) or linear attention offer improved efficiency, but whether both components are genuinely utilized remains unclear. We present a functional component ablation framework applied to two sub-1B hybrid models — Qwen3.5-0.8B (sequential: Gated DeltaNet + softmax attention) and Falcon-H1-0.5B (parallel: Mamba-2 + attention) — with a pure Transformer control (Qwen2.5-0.5B). Through group ablations, layer-wise sweeps, positional ablations, matched random controls, and perplexity analysis across […]

Ver mais

arXiv:2603.22472v1 Announce Type: new Abstract: Autonomous aerial and aquatic robots that attain mobility by perturbing their medium, such as multicopters and torpedoes, produce wake effects that act as disturbances for adjacent robots. Wake effects are hard to model and predict due to the chaotic spatio-temporal dynamics of the fluid, entangled with the physical geometry of the robots and their complex motion patterns. Data-driven approaches using neural networks typically learn a memory-less function that maps the current states of […]

Ver mais