February 2026

Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during pretraining. This assumption overlooks adversarial distribution shifts that threaten real-world reliability. To address this gap, we introduce a distributionally robust meta-learning framework that provides worst-case performance guarantees for ICL under Wasserstein-based distribution shifts. Focusing on linear self-attention Transformers, we derive a non-asymptotic bound linking adversarial […]

Ver mais

Open datasets play a crucial role in three research domains that intersect data science and education: learning analytics, educational data mining, and artificial intelligence in education. Researchers in these domains apply computational methods to analyze data from educational contexts, aiming to better understand and improve teaching and learning. Providing open datasets alongside research papers supports reproducibility, collaboration, and trust in research findings. It also provides individual benefits for authors, such as greater visibility, credibility, and citation potential. Despite […]

Ver mais

Offline safe reinforcement learning (RL) is increasingly important for cyber-physical systems (CPS), where safety violations during training are unacceptable and only pre-collected data are available. Existing offline safe RL methods typically balance reward-safety tradeoffs through constraint relaxation or joint optimization, but they often lack structural mechanisms to prevent safety drift. We propose LexiSafe, a lexicographic offline RL framework designed to preserve safety-aligned behavior. We first develop LexiSafe-SC, a single-cost formulation for standard offline safe RL, and derive safety-violation […]

Ver mais

Modern neural translation models based on the Transformer architecture are known for their high performance, particularly when trained on high-resource datasets. A standard next-token prediction training strategy, while widely adopted in practice, may lead to overlooked artifacts such as representation collapse. Previous works have shown that this problem is especially pronounced in the representation of the deeper Transformer layers, where it often fails to efficiently utilize the geometric space. Representation collapse is even more evident in end-to-end training […]

Ver mais

Quantum generative modeling, where the Born rule naturally defines probability distributions through measurement of parameterized quantum states, is a promising near-term application of quantum computing. We propose a Quantum Scrambling Born Machine in which a fixed entangling unitary — acting as a scrambling reservoir — provides multi-qubit entanglement, while only single-qubit rotations are optimized. We consider three entangling unitaries — a Haar random unitary and two physically realizable approximations, a finite-depth brickwork random circuit and analog time evolution […]

Ver mais

Reinforcement learning (RL) is a subfield of machine learning that focuses on developing models that can autonomously learn optimal decision-making strategies over time. In a recent pioneering paper, Wagner demonstrated how the Deep Cross-Entropy RL method can be applied to tackle various problems from extremal graph theory by reformulating them as combinatorial optimization problems. Subsequently, many researchers became interested in refining and extending the framework introduced by Wagner, thereby creating various RL environments specialized for graph theory. Moreover, […]

Ver mais

Controlling the longitudinal laser pulse shape in photoinjectors of Free-Electron Lasers is a powerful lever for optimizing electron beam quality, but systematic exploration of the vast design space is limited by the cost of brute-force pulse propagation simulations. We present a generative modeling framework based on Wasserstein Autoencoders to learn a differentiable latent interface between pulse shaping and downstream beam dynamics. Our empirical findings show that the learned latent space is continuous and interpretable while maintaining high-fidelity reconstructions. […]

Ver mais

Rethinking latency-sensitive DynamoDB apps for multicloud, multiregion deployment The entire process of delivering an ad occurs within 200 to 300 milliseconds. Our database lookups must complete in single-digit milliseconds. With billions of transactions daily, the database has to be fast, scalable, and reliable. If it goes down, our ad-serving infrastructure ceases to function.” – Todd Coleman, technical co-founder and chief architect at Yieldmo Yieldmo’s online advertising business depends on processing hundreds of billions of daily ad requests with […]

Ver mais

Every morning, I open Gmail, planning to check messages quickly. Then my brain gets overwhelmed with long email threads, promotions, and updates. Over a cup of coffee, my important emails like “Scheduled VPS maintenance on 2026-02-10 07:00 UTC“ get buried, and 35 minutes disappeared quickly. I even missed the 9:30 am scrum meeting! Over time, this daily habit drained my focus and energy. My email summary workflow is a lifesaver! It is technically an AI automation workflow, which […]

Ver mais