arXiv Machine Learning July 7, 2026 By Lei Sun, Yusuke Tanaka, Tomoharu Iwata

Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 4

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

arXiv:2605. 23595v2 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data.

By Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen

fine-tuning benchmarks

arXiv AI

Jul 8

Universal Algorithm-Implicit Learning

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.

By Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner

llms rag nlp multimodal benchmarks

arXiv AI

Jun 12

Meta-Learning Transformers to Improve In-Context Generalization

arXiv:2507. 05019v2 Announce Type: replace-cross Abstract: In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates.

By Lorenzo Braccaioli, Anna Vettoruzzo, Prabhant Singh, Joaquin Vanschoren, Mohamed-Rafik Bouguelia, Nicola Conci

llms safety

arXiv Machine Learning

Jul 14

Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels

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.

By Hua Qu, Yifan Li, Xiaodong Yuan

llms nlp reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jun 2

Provable Data Scaling Law for Meta Learning via Complexity Minimization

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.

By Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui

arXiv Computation and Language

Sep 2

DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification

DECSELFMASK is a decoder‑only classification method that uses unlabeled clinical text to improve performance. It creates self‑supervised training examples by masking portions of the text identified as relevant through relevance attribution, then trains the model to reconstruct the masked tokens via next‑token prediction. Experiments on 136 tasks from 1.9 M Italian hospital notes show consistent gains across five models, outperforming base models (+9.1 Macro F1), continual pretraining (+6.3), and synthetic label generation (+12.5).

By Pietro Ferrazzi, Matteo Merler, Giovanni Bonetta, Alberto Lavelli, Bernardo Magnini

One email a morning, machine-written

Related stories

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

Universal Algorithm-Implicit Learning

Meta-Learning Transformers to Improve In-Context Generalization

Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels

Provable Data Scaling Law for Meta Learning via Complexity Minimization

DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification