Unifying image-caption and image-classification datasets with prefix conditioning @ https://ai.googleblog.com/2023/06/unifying-image-caption-and-image.html Computer vision system marries image recognition and generation @ https://arxiv.org/abs/2211.09117 Unraveling GPU inference costs for fine-tuned open-source models vs closed platforms @ https://mlops.community/unraveling-gpu-inference-costs-for-fine-tuned-open-source-models-v-s-closed-platforms/ Keeping the backdoor secure in your robust machine learning model @ https://techxplore.com/news/2023-06-backdoor-robust-machine.html Long-form-video understanding and synthesis @ https://www.amazon.science/blog/long-form-video-understanding-and-synthesis DeepMind công bố robot có khả năng tự học RobotCat @ https://techxplore.com/news/2023-06-deepmind-unveils-self-training-robocat.html Rendering three-dimensional images from eye reflections with NeRF @ https://techxplore.com/news/2023-06-three-dimensional-images-eye-nerf.html
- vừa được xem lúc
Điểm tin AI tuần qua: 26/06/2023 - 02/07/2023
0 0 5
Người đăng: Dinh Trong Huy
Theo Viblo Asia