Dataset - LDM

Automatic Conditional Generation of Personalized Social Media Short Texts

A conditional language generation model with Big Five Personality (BFP) feature vectors as input context, which writes human-like short texts.
- Dataset
- JSON
Moving MNIST

Moving MNIST is a benchmark data set for video recognition. There are 10,000 samples including 8,000 for training and 2,000 for test. Each sample consists of 20 sequential gray...
- Dataset
- JSON
BLIP-2

BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models
- Dataset
- JSON
T2I-CompBench

The dataset used in the paper is not explicitly mentioned, but it is implied to be a text-to-image dataset.
- Dataset
- JSON

You can also access this registry using the API (see API Docs).

4 datasets found