arXiv Machine Learning
Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 17
Confusion-Aware Transfer Teacher Curriculum Learning Framework: Disentangling Scoring and Pacing Effects
arXiv:2606. 17706v1 Announce Type: cross Abstract: Curriculum learning couples two design choices, how samples are scored by difficulty and how harder samples are paced into training, making it difficult to attribute observed gains to either component.
arXiv AI
Aug 19
Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics
The paper investigates why curriculum learning—ordering training data from easy to hard—varies in effectiveness across reasoning tasks. By studying optimization dynamics, the authors introduce Relative Transfer, a measure of cross‑difficulty knowledge transfer, and use it to create Transfer‑aware Dynamic Curriculum Sampling (TDCS). Experiments show TDCS outperforms existing scheduling strategies on multiple reasoning benchmarks, offering a unified optimization‑based explanation for curriculum learning.
arXiv AI
Aug 18
Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain
arXiv:2608. 16164v1 Announce Type: new Abstract: Training locomotion policies for complex unstructured terrain requires a curriculum to avoid early exploration failures.
arXiv AI
Jul 10
Dual-Difficulty Curriculum Learning for Direct Preference Optimization
arXiv:2504. 07856v4 Announce Type: replace Abstract: Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dimensional view of difficulty.
arXiv Machine Learning
Jun 5
Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning
arXiv:2603. 13761v2 Announce Type: replace Abstract: Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance.
Hugging Face Trending Papers
Jun 21
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
Consistency distillation has significantly accelerated the inference of diffusion models. In this work, we reveal an intriguing asymmetry: while Logit-Normal sampling priors are highly efficacious for standard iterative generation, consistency distillation exhibits a distinctly different difficulty profile (e.