Chương trình điểm tin hàng tuần của AI Research được xây dựng nhằm mục đích giúp bạn cập nhật các xu hướng mới nhất. Nội dung của chương trình bao gồm các nội dung như sau:
- CVPR2023 đã bắt đầu! @ https://cvpr2023.thecvf.com/
- Integral Neural Networks @ https://openaccess.thecvf.com/content/CVPR2023/papers/Solodskikh_Integral_Neural_Networks_CVPR_2023_paper.pdf
- Language-Guided Music Recommendation for Video via Prompt Analogies @ https://www.danielbmckee.com/language-guided-music-for-video/
- Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning @ https://antoyang.github.io/vid2seq.html
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation @ https://openaccess.thecvf.com/content/CVPR2023/papers/Ruiz_DreamBooth_Fine_Tuning_Text-to-Image_Diffusion_Models_for_Subject-Driven_Generation_CVPR_2023_paper.pdf
- Visual Programming: Compositional visual reasoning without training @ https://openaccess.thecvf.com/content/CVPR2023/papers/Gupta_Visual_Programming_Compositional_Visual_Reasoning_Without_Training_CVPR_2023_paper.pdf
- MaskSketch: Unpaired Structure-guided Masked Image Generation @ https://masksketch.github.io/
- Voicebox: The first generative AI model for speech to generalize across tasks with SOTA performance @ https://ai.facebook.com/blog/voicebox-generative-ai-model-speech/
- Responsible AI at Google Research: AI for Social Good @ https://ai.googleblog.com/2023/06/responsible-ai-at-google-research-ai.html
- The world’s first braiding of non-Abelian anyons @ https://ai.googleblog.com/2023/06/the-worlds-first-braiding-of-non.html