Xiaolin Hu

Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning.

2020 · neural information processing systems

Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is …

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning

2025

Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, particularly in terms of prediction accuracy. However, in real-world scenarios, especially in safety-critical applications, accuracy alone is insufficient; reliable uncertainty estimates are …

StepProof: Step-by-step verification of natural language mathematical proofs

2025 · arXiv (Cornell University)

Interactive theorem provers (ITPs) are powerful tools for the formal verification of mathematical proofs down to the axiom level. However, their lack of a natural language interface remains a significant limitation. Recent advancements in large …