collaborators

11 papers

cs.LG2026

Uncertainty-Aware Reward Modeling for Stable RLHF

Licheng Pan, Haocheng Yang, Haoxuan Li +7

Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. H…

cs.CR2026

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models

Shuqiang Wang, Wei Cao, Jiaqi Weng +4

Large Reasoning Models (LRMs) are increasingly integrated into systems requiring reliable multi-step inference, yet this growing dependence exposes new vulnerabilities related to c…

cs.LG2026

Optimal Transport for LLM Reward Modeling from Noisy Preference

Licheng Pan, Haochen Yang, Haoxuan Li +8

Reward models are fundamental to Reinforcement Learning from Human Feedback (RLHF), yet real-world datasets are inevitably corrupted by noisy preference. Conventional training obje…

cs.CL2026

Robust Reward Modeling for Large Language Models via Causal Decomposition

Yunsheng Lu, Zijiang Yang, Licheng Pan +1

Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone. Most prior work weakens thes…

cs.LG2026

DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment

Hao Wang, Licheng Pan, Yuan Lu +7

Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approac…

stat.ML2026

Deep Autocorrelation Modeling for Time-Series Forecasting: Progress and Prospects

Hao Wang, Licheng Pan, Qingsong Wen +12

Autocorrelation is a defining characteristic of time-series data, where each observation is statistically dependent on its predecessors. In the context of deep time-series forecast…