Hao Wang

Licheng Pan, Haocheng Yang, Haoxuan Li et al.

Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. However, this pipeline faces two fundamental challenges: (1) reward models cannot signal when their predictions are unreliable, since they usually act as deterministic point estimators; and (2) modern group-based policy optimization can amplify unreliable reward signals, as exemplified by GRPO's uniform treatment of rewards during advantage computation. As policies explore increasingly diverse responses, these two limitations create a critical vulnerability: unreliable reward estimates may be granted disproportionate influence, triggering severe reward hacking. We propose Uncertainty-Aware Reward Modeling (UARM), which equips reward models with calibrated uncertainty via quantile-based conformal prediction and reweights GRPO advantages through heteroscedastic variance decomposition. Experiments across HelpSteer, UltraFeedback, and PKU-SafeRLHF demonstrate that UARM significantly improves reward model calibration, reduces reward hacking, and enhances downstream alignment quality compared to standard GRPO and uncertainty-agnostic baselines.

Hao Wang, Yupeng Xu, Jinghao Lin et al.

Longitudinal ophthalmic imaging analysis is an essential step for prognosis prediction in ophthalmic diseases. However, AI-assisted prognosis models are challenged by follow-up sequences, which tend to be sparse, irregularly sampled, and incomplete. Although advanced prognosis modeling methods, especially for the methods based on neural controlled differential equations (NCDEs), provide a principled continuous-time framework for sparse and irregular longitudinal data. Unfortunately, two major concerns remain unsolved in clinical follow-up modeling. First, the smooth latent dynamics of standard NCDEs is poorly matched to abrupt pathological changes induced by therapeutic intervention, lesion recurrence, or long follow-up gaps. Second, numerical integration over long horizons can accumulate errors, which will produce unstable latent trajectories and weakened class discrimination. To address these challenges, we propose ImProNCDE, an impulse-corrected NCDE framework with prototype learning for longitudinal ophthalmic prognosis prediction. To capture abrupt pathological changes beyond smooth latent dynamics, ImProNCDE introduces Residual Impulse Calibration (RIC), which injects residual-based impulse corrections at visit times and then recalibrates the latent state when observations deviate from continuous predictions. To further mitigate error accumulation over long horizons, we introduce a Prototype-guided Trajectory Stabilizer (PTS), which aims to attract latent trajectories toward learnable prognosis prototypes to reduce class overlap and which ultimately improves long-horizon stability. Experiments on multiple private and public longitudinal ophthalmic datasets (totalling over 1206 samples) show that ImProNCDE outperforms existing SOTA methods focusing on sequence modeling.