the learning sciences

KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning

arXiv:2605.31099v1 Announce Type: new Abstract: Science news is an important medium to communicate discoveries between the research communities and the public. Yet, most metrics for generated or summarized text evaluate semantic similarity and factual consistency, but do not measure how much knowledge readers learn from the news.

EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management

arXiv:2606.03841v1 Announce Type: new Abstract: Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their static action sets and lack of principled long-horizon context management, hindering their ability to accumulate reusable experience across tasks and operate reliably in multi-stage, iterative data science pipelines.

I hated writing–until I learned there's a science to it(2024)

Deep networks learn to parse uniform-depth context-free languages from local statistics

Announce Type: replace-cross Abstract: Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal representations of Large Language Models (LLMs) support their ability to parse text when predicting the next word, while representing semantic notions independently of surface form. Yet, which data statistics make these feats possible, and how much data is required, remain largely...

Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors

Computer Science > Machine Learning [Submitted on 31 May 2026] Title:Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors View PDF HTML (experimental)Abstract:We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic information to justify committed exploitation of the averaging distribution?

Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors

Computer Science > Machine Learning [Submitted on 31 May 2026 (v1), last revised 2 Jun 2026 (this version, v2)] Title:Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors View PDF HTML (experimental)Abstract:We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic information to justify committed exploitation of the averaging distribution?

DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers

arXiv:2605.30456v1 Announce Type: new Abstract: Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these problems are often accompanied by rich domain knowledge derived from physical laws, operational requirements, and expert heuristics.

GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting

arXiv:2606.06881v1 Announce Type: new Abstract: Blood glucose forecasting models are foundational for modern diabetes management systems, as reliable short-term predictions can enable proactive interventions, support automated insulin delivery, and reduce the risk of hypo- and hyperglycemic events. From a modeling perspective, glucose forecasting poses unique challenges due to heterogeneous physiological dynamics across diabetes populations. Traditional machine learning and deep learning...

Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing

arXiv:2604.07366v2 Announce Type: replace Abstract: Partial differential equations (PDEs) govern nearly every physical process in science and engineering, but solving them at scale remains prohibitively expensive. Generative AI has transformed language, vision, and protein science, but learned PDE solvers have not undergone a comparable shift. Existing paradigms each capture part of the problem.

Can LLMs Beat Classical Hyperparameter Optimization Algorithms?

Computer Science > Machine Learning [Submitted on 25 Mar 2026 (v1), last revised 17 Apr 2026 (this version, v5)] Title:Can LLMs Beat Classical Hyperparameter Optimization Algorithms?