Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Small-Margin Preferences Still Matter-If You Train Them Right
Jinlong Pang, Zhaowei Zhu, Na Di +4
Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficul…
cs.AI2025
Incentivizing High-quality Participation From Federated Learning Agents
Jinlong Pang, Jiaheng Wei, Yifan Hua +2
Federated learning (FL) provides a promising paradigm for facilitating collaboration between multiple clients that jointly learn a global model without directly sharing their local…