The paper proposes a novel online learning algorithm that achieves an interval regret bound scaling with gradient variation, providing strong theoretical guarantees for non-stationary environments.

A hybrid active-online learning framework is proposed for label-efficient concept drift adaptation in optical network failure detection, achieving high accuracy and AUC scores with minimal samples and…

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

OrcaRouter is a production-ready LLM router that uses a hybrid offline-online learning approach to efficiently select the best large language model for an incoming query, achieving high accuracy at lo…

This paper provides non-asytotic sample complexity guarantees for the Navigate and Stop algorithm in online tabular Reinforcement Learning, identifying additional attributes that affect the overall sa…

This paper introduces a mechanistic neuronal network model for multilayer learning, offering biological insights and an alternative to backpropagation.

The paper introduces TRON, an online, rule-verifiable environment substrate that generates an unbounded stream of fresh, controllable visual reasoning training instances, significantly improving RL pe…

This paper shows that finite unions of intersecting affine modules in one dimension are efficiently exactly learnable using equivalence and subset queries.

This study compares different levels of LLM access in a statistics course, finding that structured, guided use significantly improves students' reasoning skills and independent learning compared to un…

The paper introduces a new anytime-valid inference method to correct split selection in online decision trees, providing robust statistical guarantees for streaming data that existing methods lack.

This paper shows that stochastic nonconvex optimization can be reduced to ordinary static regret minimization in online convex optimization, and establishes convergence rates for smooth and Lipschitz…

This paper develops a unified spectral analysis framework to explain how knowledge transfer (KT) works across different machine learning regimes, such as Knowledge Distillation and Weak-to-Strong gene…

The paper introduces an LLM-based pipeline that tags learning resources with structured competencies, achieving strong performance while providing traceable evidence and leveraging graph constraints.

This paper compares two methods for assessing student teams in tabletop exercises using data from learning platforms and evaluates their validity and reliability.

The paper proposes an interpretable, AI-driven decision layer that ranks course topics needing attention using multiple student and teacher signals, successfully identifying learning gaps before forma…

This paper presents a deterministic algorithm achieving an expected competitive ratio of O(1) for Euclidean online TSP in high dimensions and O(log n) for d = 1, improving upon previous O(sqrt(n)) and…