27 citations · 98 across the 31 of their papers we have counts for
4 papers · 1 filter
When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
Xiaogeng Liu, Xinyan Wang, Yingzi Ma +2
On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly trea…
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
Xinyan Wang, Xiaogeng Liu, Ming Pei +1
Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecess…
Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
Yechao Zhang, Shengshan Hu, Leo Yu Zhang +5
Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different…
Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation
Xiaogeng Liu, Haoyu Wang, Yechao Zhang +2
The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models. In this paper, we mainly focus on design…