5 papers
f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
Rajdeep Haldar, Lantao Mei, Guang Lin +2
Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding…
Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression
Weiyi He, Yue Xing
Positional encoding (PE) is a core architectural component of Transformers, yet its impact on the Transformer's generalization and robustness remains unclear. In this work, we prov…
CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization
Xikai Yang, Sebastian Sun, Yilin Li +3
Ad ranking systems must simultaneously optimize multiple objectives including click-through rate (CTR), conversion rate (CVR), revenue, and user experience metrics. However, produc…
Contrastive Learning-Based Dependency Modeling for Anomaly Detection in Cloud Services
Yue Xing, Yingnan Deng, Heyao Liu +3
This paper addresses the challenges of complex dependencies and diverse anomaly patterns in cloud service environments by proposing a dependency modeling and anomaly detection meth…
How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?
Meiqi Liu, Zhuoqun Huang, Yue Xing
With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of d…