2 papers
cs.AI2026
Generative Auto-Bidding with Unified Modeling and Exploration
Mingming Zhang, Feiqing Zhuang, Na Li +7
Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approaches modeled bidding as a Ma…
cs.CL2024
MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples
Shuo Xie, Fangzhi Zhu, Jiahui Wang +6
Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Re…