8 papers
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
Xuyang Zhong, Qizhang Li, Yiwen Guo +1
We propose DualOptim+, a novel optimization framework for improving machine unlearning in large language models. It introduces a base state to capture common representations shared…
BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics
Siddharth Viswanath, Panayiotis Ketonis, Chen Liu +11
Brain activity unfolds as coordinated patterns across regions over time, and modeling these dynamics is a central goal in computational neuroscience. Because activity is distribute…
MoleCode unlocks structural intelligence in large language models
Zhiyuan Yan, Chen Liu, Boxuan Zhao +8
Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses…
PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks
Jingning Xu, Haochen Luo, Chen Liu
Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computa…
DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
Xuyang Zhong, Haochen Luo, Chen Liu
Existing machine unlearning (MU) approaches exhibit significant sensitivity to hyperparameters, requiring meticulous tuning that limits practical deployment. In this work, we first…
Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
Xuyang Zhong, Yixiao Huang, Chen Liu
This paper studies fast adversarial training against sparse adversarial perturbations bounded by norm. We demonstrate the challenges of employing -step attacks on bo…
Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation
Xuyang Zhong, Chen Liu
This work studies sparse adversarial perturbations, including both unstructured and structured ones. We propose a framework based on a white-box PGD-like attack method named Sparse…
Towards Mitigating Architecture Overfitting on Distilled Datasets
Xuyang Zhong, Chen Liu
Dataset distillation methods have demonstrated remarkable performance for neural networks trained with very limited training data. However, a significant challenge arises in the fo…