18 citations · 36 across the 21 of their papers we have counts for
7 papers · 1 filter
MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning
Guanglong Sun, Kanglei Zhou, Liyuan Wang +6
General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic y…
ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models
Guanglong Sun, Shuang Cui, Bo Lei +6
Test-time adaptation (TTA) of vision-language models (VLMs) is essential for their robust deployment in dynamic, real-world environments. However, existing TTA methods often adapt…
Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
Yunrui Yu, Xuxiang Feng, Pengda Qin +5
Adversarial robustness evaluation faces a critical challenge as new defense paradigms emerge that can exploit limitations in existing assessment methods. This paper reveals that Du…
Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
Yunrui Yu, Hang Su, Jun Zhu
This work investigates the critical role of activation function curvature -- quantified by the maximum second derivative -- in adversarial robustness. Using the Recursi…
Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving
Chang Su, Zhongkai Hao, Zhizhou Zhang +4
Large language models (LLMs) with reasoning abilities have demonstrated growing promise for tackling complex scientific problems. Yet such tasks are inherently domain-specific, unb…
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
Guanglong Sun, Hongwei Yan, Liyuan Wang +5
To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collect…
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
Guanglong Sun, Siyuan Zhang, Liyuan Wang +3
Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the…