Search Results for author:
Found 13 papers, 5 papers with code
T2I-ConBench: Text-to-Image Benchmark for Continual Post-training
To address this, we introduce T2I-ConBench, a unified benchmark for continual post-training of text-to-image models.
A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning
Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for data removal, forming the Continual Learning-Unlearning (CLU) paradigm.
MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes
In today's over-parameterized models, dominated by neural networks, a common approach is to manually relabel data and fine-tune the well-trained model.
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
Approximate MU is a practical method for large-scale models.
Flat-LoRA: Low-Rank Adaption over a Flat Loss Landscape
Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computational and memory costs.
Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection
In the open world, detecting out-of-distribution (OOD) data, whose labels are disjoint with those of in-distribution (ID) samples, is important for reliable deep neural networks (DNNs).
Towards Natural Machine Unlearning
Towards more \textit{natural} machine unlearning, we inject correct information from the remaining data to the forgetting samples when changing their labels.
Friendly Sharpness-Aware Minimization
By decomposing the adversarial perturbation in SAM into full gradient and stochastic gradient noise components, we discover that relying solely on the full gradient component degrades generalization while excluding it leads to improved performance.
Remaining-data-free Machine Unlearning by Suppressing Sample Contribution
We first theoretically discover that sample's contribution during the process will reflect in the learned model's sensitivity to it.
Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
Based on self-fitting, we provide new insights into the existing methods to mitigate CO and extend CO to multi-step adversarial training.
Trainable Weight Averaging: A General Approach for Subspace Training
Training deep neural networks (DNNs) in low-dimensional subspaces is a promising direction for achieving efficient training and better generalization performance.
Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet
AoA enjoys a significant increase in transferability when the traditional cross entropy loss is replaced with the attention loss.
DAmageNet: A Universal Adversarial Dataset
Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence.
