We present SynthCLIP, a novel framework for training CLIP models with entirely synthetic
text-image pairs, significantly departing from previous methods relying on real data …

Image captioning aims to automatically generate captions for images by learning a cross-
modal generator from vision to language. The large amount of image-text pairs required for …

Image captioning requires numerous annotated image-text pairs, resulting in substantial
annotation costs. Recently, large models (eg diffusion models and large language models) …

We introduce NOVIC, an innovative uNconstrained Open Vocabulary Image Classifier that
uses an autoregressive transformer to generatively output classification labels as language …

The success of existing cross-modal retrieval (CMR) methods heavily rely on the assumption
that the annotated cross-modal correspondence is faultless. In practice, however, the …

While image captioning is an essential field of vision language models (VLM), a lack of
continuity between the learning objective and final performance metrics of VLMs …

Pretraining robust vision or multimodal foundation models (eg, CLIP) relies on large-scale
datasets that may be noisy, potentially misaligned, and have long-tail distributions. Previous …

In this report, we introduce NICE project\footnote {\url {https://nice. lgresearch. ai/}} and share
the results and outcomes of NICE challenge 2023. This project is designed to challenge the …

Large repositories of image-caption pairs are essential for the development of vision-
language models. However, these datasets are often extracted from noisy data scraped from …

In this report we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation)
project and share the results and outcomes of 2023 challenge. This project is designed to …