6 papers
Train Locally, Learn Together: Distributed Multi-Agent Training via ADMM
Yiwei Chen, Changsheng Wang, Yicheng Lang +3
Multi-agent systems (MAS) can outperform individual language-model agents by combining specialized roles, diverse reasoning processes, and collaborative decision-making. However, c…
On the Plasticity Collapse in Continual Machine Unlearning
Yingdan Shi, Xiang Xu, Kaize Ding +2
Machine unlearning enables deep neural networks to selectively remove the influence of specific data in response to privacy and regulatory requirements. While prior work largely st…
CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
Chongyu Fan, Yihua Zhang, Jinghan Jia +2
Large reasoning models (LRMs), such as OpenAI's o1 and DeepSeek-R1, harness test-time scaling to perform multi-step reasoning for complex problem-solving. This reasoning process, e…
Deep Adversarial Defense Against Multilevel-Lp Attacks
Ren Wang, Yuxuan Li, Alfred Hero
Deep learning models have shown considerable vulnerability to adversarial attacks, particularly as attacker strategies become more sophisticated. While traditional adversarial trai…
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
Chongyu Fan, Jiancheng Liu, Alfred Hero +1
The trustworthy machine learning (ML) community is increasingly recognizing the crucial need for models capable of selectively 'unlearning' data points after training. This leads t…
Bridging Models to Defend: A Population-Based Strategy for Robust Adversarial Defense
Ren Wang, Yuxuan Li, Can Chen +6
Adversarial robustness is a critical measure of a neural network's ability to withstand adversarial attacks at inference time. While robust training techniques have improved defens…