arXiv:2606. 02008v1 Announce Type: cross Abstract: Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases.
Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon.
arXiv:2409. 03682v2 Announce Type: replace Abstract: Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems.
arXiv:2509.18349v4 Announce Type: replace Abstract: Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number of l...
The paper introduces two algorithms, MAGE and SPELL, that enable efficient data attribution in neural networks by estimating a large influence matrix from a limited number of measurements. These methods leverage existing metagradient techniques without additional computational overhead, addressing the challenge of predicting the impact of removing training data in non‑convex models. Experiments show that MAGE and SPELL outperform current baselines across various training scales and measurement budgets.
arXiv:2602. 14761v2 Announce Type: replace-cross Abstract: Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability.
arXiv:2607. 09796v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has become an important method for aligning large language models (LLMs) with human preferences because it removes the need for explicit reward modeling and reinforcement learning optimization.
arXiv:2606. 04503v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has greatly advanced large reasoning models (LRMs), but it requires timely training on a huge fully-annotated dataset.
arXiv:2607. 02850v1 Announce Type: new Abstract: Meta-learning without labeled data is crucial for real-world applications, where obtaining labeled datasets can be expensive or restricted due to privacy concerns.
arXiv:2606. 15734v1 Announce Type: cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities.
Data Attribution at Scale via Influence Matrix Estimation proposes a scalable approach to quantify how individual training examples influence a model’s predictions. The authors introduce two algorithms, MAGE and SPELL, that reconstruct an influence matrix from a limited number of measurements without extra computational cost, improving over existing baselines across various training scales and budgets.
arXiv:2607. 18830v1 Announce Type: cross Abstract: Model-Agnostic Meta-Learning (MAML) is a widely used framework for reinforcement learning (RL) that enables efficient transfer by learning global policy parameters that can be rapidly adapted to new tasks.