期刊&会议

ICLR

International Conference on Learning Representations · 会议 · Machine Learning

2025-10-27 至 2025-10-27 共收录 2 篇

2505.19527 2025-10-27 cs.LG cs.AI math.OC

Rolling Ball Optimizer: Learning by ironing out loss landscape wrinkles

Mohammed Djameleddine Belgoumri, Mohamed Reda Bouadjenek, Hakim Hacid, Imran Razzak, Sunil Aryal

机构 * Deakin University（德肯大学）； Technology Innovation Institute（技术创新研究所）； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

Comments Submitted for review to ICLR 2026

2410.12854 2025-10-27 cs.CL cs.AI

TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees

Weibin Liao, Xu Chu, Yasha Wang

机构 * School of Computer Science, Peking University（北京大学计算机科学系）； Center on Frontiers of Computing Studies, Peking University（北京大学前沿计算研究中心）； National Research and Engineering Center of Software Engineering, Peking University（北京大学软件工程研究中心）

Comments Accepted by ICLR 2025