Haoyi Yang — accepted AI-conference papers

2025

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding

Indraneil Paul, Haoyi Yang, Goran Glavaš, Kristian Kersting, Iryna Gurevych

ICLR 2025poster

Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes in data sourcing and filtering strategies. In particular, research exploring modifications to Code-LMs' pre-training obj…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Curriculum Reinforcement Learning via Constrained Optimal Transport

Pascal Klink, Haoyi Yang, Carlo D’Eramo, Jan Peters, Joni Pajarinen

ICML 2022spotlight

Curriculum reinforcement learning (CRL) allows solving complex tasks by generating a tailored sequence of learning tasks, starting from easy ones and subsequently increasing their difficulty. Although the potential of curricula in RL has been clearly shown in a variety of works, it is less clear how…

Cited by 46 Source ↗PDF ↗code ↗Scholar ↗