paper-with-me

Papers

HuCurl: Human-induced Curriculum Discovery

2023-07-14 · Mohamed Elgaar, Hadi Amiri

We introduce the problem of curriculum discovery and describe a curriculum learning framework capable of discovering effective curricula in a curriculum space based on prior knowledge about sample difficulty. Using annotation entropy and loss as measures of difficulty, we show that (i): the top-performing discovered curricula for a given model and dataset are often non-monotonic as opposed to monotonic curricula in existing literature, (ii): the prevailing easy-to-hard or hard-to-easy transition curricula are often at the risk of underperforming, and (iii): the curricula discovered for smaller datasets and models perform well on larger datasets and models respectively. The proposed framework encompasses some of the existing curriculum learning approaches and can discover curricula that outperform them across several NLP tasks.

📄 PDF Abstract BibTeX arXiv:2307.07412

Code (1)

CLU-UML/Curriculum-Discovery 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics

2026-08-18 · Zhikai Ding, Ziyi Ye arxiv

Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies substantially across reasoning tasks, suggesting …

Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning

2017-08-07 · Sébastien Forestier, Rémy Portelas, Yoan Mollard, Pierre-Yves Oudeyer

Intrinsically motivated spontaneous exploration is a key enabler of autonomous developmental learning in human children. It enables the discovery of skill repertoires through autotelic learning, i.e. the self-generation,…

Developmental LearningMulti-Goal Reinforcement LearningReinforcement LearningSelf-Supervised Learning

ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning

2026-04-30 · Chengcao Yang arxiv

We propose a paradigm shift toward open-ended curriculum self-play: rather than learning to answer on a fixed prompt set, a unified policy learns to question: generating verifiable problems, solving them, and turning ver…

Cognitive Training for Language Models: Towards General Capabilities via Cross-Entropy Games

2026-03-23 · Clément Hongler, Franck Gabriel, Valentin Hartmann, Arthur Renard 외 arxiv

Defining a constructive process to build general capabilities for language models in an automatic manner is considered an open problem in artificial intelligence. Towards this, we consider the problem of building a curri…

From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models

2026-05-19 · Jianan Yang, Yiran Wang, Shuai Li, Fujun Cao 외 arxiv

Physics-informed neural networks (PINNs) offer a mesh-free framework for solving partial differential equations (PDEs), yet training often suffers from gradient pathologies, spectral bias, and poor convergence, especiall…