Inspired by Adrian Colyer (known for the morning paper) and Vitaly Kurin (known as YobiByte), I decided to share summaries of the papers I read for my research and for fun.
I usually try to stay up-to-date through the latest conferences, as well as with notifications from Google Scholar and ArXiv. Recently, I also started using and fine-tuning scholar-inbox, a paper recommender system developed at the University of Tübingen [news].
18 Lu, Haodong, et al. "Learning with Mixture of Prototypes for Out-of-Distribution Detection." (ICLR2024) [summary], [source]
17 Bai, Haoyue, et al. "HYPO: Hypershperical Out-of-Distribution Generalization." (ICLR2024) [summary], [source]
16 Chen, Qiuyi, et al. "Compressing Latent Space via Least Volume." (ICLR2024) [summary], [source]
15 Liang, Jian, et al. "Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization." (ICML2024) [summary], [source]
14 Jiang, Wenyu, et al. "DOS: Diverse Outlier Sampling for Out-of-Distribution Detection." (ICLR 2024) [summary], [source]
13 Franchi, Gianni, et al. "Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models." (CVPR 2024) [summary], [source]
12 Ming, Yifei, et al. "How to exploit hyperspherical embeddings for out-of-distribution detection?." (ICLR 2023) [summary], [source]
11 Zaeemzadeh, Alireza, et al. "Out-of-distribution detection using union of 1-dimensional subspaces." (CVPR 2021) [summary], [source]
10 Wilson, Samuel, et al. "Hyperdimensional feature fusion for out-of-distribution detection." (WACV 2023) [summary], [source]
09 Fu, Stephanie, et al. "FeatUp: A Model-Agnostic Framework for Features at Any Resolution." (ICLR 2024) [summary], [source]
08 Balestriero, Randall, Jerome Pesenti, and Yann LeCun. "Learning in high dimension always amounts to extrapolation." (arXiv 2021) [summary], [source]
07 Crisostomi, Donato, et al. "From Charts to Atlas: Merging Latent Spaces into One." (PMLR 2023) [summary], [source]
06 Cannistraci, Irene, et al. "From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication." (ICLR 2024) [summary], [source]
05 Moschella, Luca, et al. "Relative Representations Enable Zero-Shot Latent Space Communication". (ICLR 2023) [summary], [source]
04 Liu, Jiahui, et al. "Few-shot Learning for Inference in Medical Imaging with Subspace Feature Representations." (arXiv 2023) [summary], [source]
03 Stoica, George, et al. "ZipIt! Merging Models from Different Tasks without Training." (arXiv 2023) [summary], [source]
02 Wortsman, Mitchell, et al. "Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time." (ICML 2022) [summary], [source]
01 Yang, Yuncheng, et al. "Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentation." (MICCAI 2023) [summary], [source]