Search Results for author:
Found 10 papers, 4 papers with code
Catastrophic Overfitting: A Potential Blessing in Disguise
To tackle this issue, we initially employ the feature activation differences between clean and adversarial examples to analyze the underlying causes of CO. Intriguingly, our findings reveal that CO can be attributed to the feature coverage induced by a few specific pathways.
Separable Multi-Concept Erasure from Diffusion Models
Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of copyrighted artistic styles.
EipFormer: Emphasizing Instance Positions in 3D Instance Segmentation
It enhances the initial instance positions through weighted farthest point sampling and further refines the instance positions and proposals using aggregation averaging and center matching.
Fast Adversarial Training with Smooth Convergence
To address this, we analyze the training process of prior FAT work and observe that catastrophic overfitting is accompanied by the appearance of loss convergence outliers.
Temporal Knowledge Graph Reasoning Triggered by Memories
Specifically, the transient learning network considers transient memories as a static knowledge graph, and the time-aware recurrent evolution network learns representations through a sequence of recurrent evolution units from long-short-term memories.
Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More
Our work highlights several novel perspectives and opportunities for implementing randomized algorithms for deep learning on modern CPUs.
A Truly Constant-time Distribution-aware Negative Sampling
Softmax classifiers with a very large number of classes naturally occur in many applications such as natural language processing and information retrieval.
A Tale of Two Efficient and Informative Negative Sampling Distributions
Unfortunately, due to the dynamically updated parameters and data samples, there is no sampling scheme that is provably adaptive and samples the negative classes efficiently.
What is the Largest Sparsity Pattern that Can Be Recovered by 1-Norm Minimization?
In the case of the partial discrete Fourier transform, our characterization of the largest sparsity pattern that can be recovered requires the unknown signal to be real and its dimension to be a prime number.
A Framework for Developing and Evaluating Word Embeddings of Drug-named Entity
We investigate the quality of task specific word embeddings created with relatively small, targeted corpora.
