8 papers
Dual-Channel Robust Group-Relative Policy Optimization via Advantage and Sequence-Weight Estimation
Zhongyi Li, Wan Tian, Xiang Xu +4
Group-relative policy optimization relies on reward-derived advantages and sequence-level likelihood weights, both of which can be sensitive to localized outliers. Extreme rewards…
STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking
Wan Tian, Zhongyi Li, Xiang Xu +3
Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training score without improving the under…
Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation
Wan Tian, Zhongyi Li, Yawen Li +3
Mixed human-LLM documents require locating authorship transitions from detector scores whose reliability varies across text units. Existing weighted mean contrasts are vulnerable t…
A Unified Detection Framework for AI-Related Content and Artifacts
Xifeng Zhang, Tao Hu, Yijie Peng +1
Artificial intelligence (AI) is a double-edged sword: while it has achieved remarkable success across a wide range of domains, its deployment also calls for effective oversight and…
Machine Learning-Assisted High-Dimensional Matrix Estimation
Wan Tian, Hui Yang, Zhouhui Lian +2
Efficient estimation of high-dimensional matrices-including covariance and precision matrices-is a cornerstone of modern multivariate statistics. Most existing studies have focused…
Adaptive Robust Estimator for Multi-Agent Reinforcement Learning
Zhongyi Li, Wan Tian, Jingyu Chen +8
Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that…
Sharper Generalization Bounds for Transformer
Yawen Li, Tao Hu, Zhouhui Lian +4
This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer…
Series Expansion of Probability of Correct Selection for Improved Finite Budget Allocation in Ranking and Selection
Xinbo Shi, Yijie Peng, Bruno Tuffin
This paper addresses the challenge of improving finite sample performance in Ranking and Selection by developing a Bahadur-Rao type expansion for the Probability of Correct Selecti…