17 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…
Projection-Based Outlier Detection in Interval-Valued Functional Data
Hao Xu, Wan Tian, Zhongfeng Qin
Outlier detection is a fundamental task for ensuring reliable statistical modeling and inference. Interval-valued functional data (IVFD), in which each observation is represented b…
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…
Estimating Precision Matrices for High-Dimensional Interval-Valued Data
Zhongfeng Qin, Hao Xu, Wenhao Cui +1
In the field of statistical learning and data analysis, estimating precision matrices (i.e., the inverse of covariance matrices) is a critical task, particularly for understanding…
Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards
Huiming Zhang, Binghan Li, Wan Tian +1
Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or sub-Gau…
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…
Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
Hui Yang, Tao Ren, Jinyang Jiang +2
Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existi…
Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
Zhongyi Li, Wan Tian, Jinju Chen +4
Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assi…
RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training
Tao Ren, Jinyang Jiang, Hui Yang +10
Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, suc…
Interval-Valued Time Series Classification Using -Distance
Wan Tian, Zhongfeng Qin
In recent years, modeling and analysis of interval-valued time series have garnered increasing attention in econometrics, finance, and statistics. However, these studies have predo…
Block Toeplitz Sparse Precision Matrix Estimation for Large-Scale Interval-Valued Time Series Forecasting
Wan Tian, Zhongfeng Qin
Modeling and forecasting interval-valued time series (ITS) have attracted considerable attention due to their growing presence in various contexts. To the best of our knowledge, th…
Adaptive Classification of Interval-Valued Time Series
Wan Tian, Zhongfeng Qin
In recent years, the modeling and analysis of interval-valued time series have garnered significant attention in the fields of econometrics and statistics. However, the existing li…
A model-free feature extraction procedure for interval-valued time series prediction
Wan Tian, Zhongfeng Qin, Tao Hu
In this paper, we present a novel feature extraction procedure to predict interval-valued time series by combing transfer learning and imaging approaches. Initially, we represent i…