One of the odd statistical outliers from the first two months can be found in the list of penalty-minute leaders. While the ...

Abstract: State-of-the-art V-SLAM pipelines utilize robust cost functions and outlier rejection techniques to remove incorrect correspondences. However, these methods are typically fine-tuned to ...

Abstract: We present a novel solution to the problem of subspace outlier detection that does not assume prior knowledge of the number of outliers nor the dimension of the inliers subspace. The ...

This is the code for the paper [OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models](https://arxiv.org/abs/2306. ...