29 citations · 93 across the 15 of their papers we have counts for
15 papers
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
Gabriel J. Perin, Runjin Chen, Xuxi Chen +3
Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding…
Make Optimization Once and for All with Fine-grained Guidance
Mingjia Shi, Ruihan Lin, Xuxi Chen +8
Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks. L2O paradigms achieve great outcomes, e.g., refitting optimizer, generating unseen solu…
Extracting and Understanding the Superficial Knowledge in Alignment
Runjin Chen, Gabriel Jacob Perin, Xuxi Chen +5
Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsi…
Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization
Xuxi Chen, Zhendong Wang, Daouda Sow +5
In the rapidly advancing arena of large language models (LLMs), a key challenge is to enhance their capabilities amid a looming shortage of high-quality training data. Our study st…
Rethinking PGD Attack: Is Sign Function Necessary?
Junjie Yang, Tianlong Chen, Xuxi Chen +2
Neural networks have demonstrated success in various domains, yet their performance can be significantly degraded by even a small input perturbation. Consequently, the construction…
Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
Xuxi Chen, Yu Yang, Zhangyang Wang +1
Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar genera…
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
Shiwei Liu, Tianlong Chen, Zhenyu Zhang +4
Sparse Neural Networks (SNNs) have received voluminous attention predominantly due to growing computational and memory footprints of consistently exploding parameter count in large…
M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation
Junjie Yang, Xuxi Chen, Tianlong Chen +2
Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks by ``overfitting" specific task type, leadi…
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
Tianlong Chen, Xuxi Chen, Xiaolong Ma +2
The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i.e., winning tickets) that can be trained in isolation to match full accuracy. D…
You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership
Xuxi Chen, Tianlong Chen, Zhenyu Zhang +1
Despite tremendous success in many application scenarios, the training and inference costs of using deep learning are also rapidly increasing over time. The lottery ticket hypothes…
Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Xiaolong Ma, Geng Yuan, Xuan Shen +8
There have been long-standing controversies and inconsistencies over the experiment setup and criteria for identifying the "winning ticket" in literature. To reconcile such, we rev…
Efficient Lottery Ticket Finding: Less Data is More
Zhenyu Zhang, Xuxi Chen, Tianlong Chen +1
The lottery ticket hypothesis (LTH) reveals the existence of winning tickets (sparse but critical subnetworks) for dense networks, that can be trained in isolation from random init…
GANs Can Play Lottery Tickets Too
Xuxi Chen, Zhenyu Zhang, Yongduo Sui +1
Deep generative adversarial networks (GANs) have gained growing popularity in numerous scenarios, while usually suffer from high parameter complexities for resource-constrained rea…
A Unified Lottery Ticket Hypothesis for Graph Neural Networks
Tianlong Chen, Yongduo Sui, Xuxi Chen +2
With graphs rapidly growing in size and deeper graph neural networks (GNNs) emerging, the training and inference of GNNs become increasingly expensive. Existing network weight prun…
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
Xuxi Chen, Wuyang Chen, Tianlong Chen +4
Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i.e., learning binary classifiers from a large amount of unlabeled data and a few labeled…