2 papers
cs.LG2026
Path-Coupled Bellman Flows for Distributional Reinforcement Learning
Boyang Xu, Qing Zou, Siqin Yang +1
Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based…
cs.CL2026
Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
Junyu Lu, Deyi Ji, Xuanyi Liu +5
Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single supervision signal. This par…