arXiv:2603.07467v1 Announce Type: new Abstract: This monograph provides a rigorous overview of theoretical and methodological aspects of probabilistic inference and learning with Stein’s method. Recipes are provided for constructing Stein discrepancies from Stein operators and Stein sets, and properties of these discrepancies such as computability, separation, convergence detection, and convergence control are discussed. Further, the connection between Stein operators and Stein variational gradient descent is set out in detail. The main definitions and results are precisely stated, and […]

Ver mais

Adversarial robustness in RL is difficult because perturbations affect entire trajectories: strong attacks can break learning, while weak attacks yield little robustness, and the appropriate strength varies by state. We propose $α$-reward-preserving attacks, which adapt the strength of the adversary so that an $α$ fraction of the nominal-to-worst-case return gap remains achievable at each state. In deep RL, we use a gradient-based attack direction and learn a state-dependent magnitude $ηle η_{mathcal B}$ selected via a critic $Q^π_α((s,a),η)$ trained […]

Ver mais

arXiv:2601.06715v1 Announce Type: cross Abstract: Score-based diffusion models have become a powerful framework for generative modeling, with score estimation as a central statistical bottleneck. Existing guarantees for score estimation largely focus on light-tailed targets or rely on restrictive assumptions such as compact support, which are often violated by heavy-tailed data in practice. In this work, we study conventional (Gaussian) score-based diffusion models when the target distribution is heavy-tailed and belongs to a Sobolev class with smoothness parameter $beta>0$. […]

Ver mais

arXiv:2506.15735v2 Announce Type: replace-cross Abstract: Identifying inputs that trigger specific behaviours or latent features in language models could have a wide range of safety use cases. We investigate a class of methods capable of generating targeted, linguistically fluent inputs that activate specific latent features or elicit model behaviours. We formalise this approach as context modification and present ContextBench — a benchmark with tasks assessing core method capabilities and potential safety applications. Our evaluation framework measures both elicitation strength […]

Ver mais

Today, it might be easy to grow accustomed to the idea that more data equals better insights. Companies can track every click through the sales funnel, analyze product usage, and scrape public websites to gather leads or competitor insights. However, 68% of data, according to research done by IDC for Seagate, sits unused, growing stale by the day. But as any data engineer will tell you, collecting data is only the first step. Cleaning, deduplicating, structuring, and integrating […]

Ver mais

arXiv:2603.06687v1 Announce Type: new Abstract: Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications such as disaster management, traffic planning, embodied navigation, world modeling, and geography education. Although recent vision-language models (VLMs) have advanced image geo-localization using cues like landmarks and road signs, their ability to reason about temporal signals and physically grounded spatial cues remains limited. To address this gap, we introduce TimeSpot, a benchmark for evaluating real-world geo-temporal […]

Ver mais

A key operation for massive data series collection analysis is similarity search. According to recent studies, SAX-based indexes offer state-of-the-art performance for similarity search tasks. However, their performance lags under high-frequency, weakly correlated, excessively noisy, or other dataset-specific properties. In this work, we propose Deep Embedding Approximation (DEA), a novel family of data series summarization techniques based on deep neural networks. Moreover, we describe SEAnet, a novel architecture especially designed for learning DEA, that introduces the Sum of […]

Ver mais

The Day Your LLM Stops Talking and Starts Doing There’s a moment in every LLM project where you realize the “chat” part is the easy bit. The hard part is everything that happens between the user request and the final output: gathering missing facts, choosing which tools to call (and in what order), handling failures, remembering prior decisions, and not spiraling into confident nonsense when the world refuses to match the model’s assumptions. That’s the moment you’re no […]

Ver mais