A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Laurianne David, Amol Thakkar, Rocío Mercado, et al.
This review catalogs molecular representations for AI-driven drug discovery, serving as a practical guide for researchers new to chemical syntax.
Ronan Collobert, Jason Weston, Léon Bottou, et al.
A unified neural network architecture that learns internal representations from unlabelled data achieves state-of-the-art on multiple NLP tasks without task-specific feature engineering.
Craig Boutilier, Taraneh Dean, Steve Hanks
This paper surveys how structural properties of MDPs can be exploited via AI-style representations to ease the computational burden of planning under uncertainty.
Unknown
CLIP learns visual representations from 400M image-text pairs via contrastive pre-training, enabling zero-shot transfer to diverse tasks.
Unknown
Florence is a computer vision foundation model that adapts to diverse tasks by expanding representations across coarse-to-fine, static-to-dynamic, and RGB-to-multimodal dimensions.
Unknown
This paper uses synthetic data to study how pretrained large language models form representations during in-context learning.
Danijar Hafner, J. Pašukonis, Jimmy Ba, et al.
Dreamer learns a world model from latent representations to enable planning and strong task performance across diverse domains.
Unknown
This paper improves vision features for vision-language tasks by developing an enhanced object detection model.