# Dual-Encoder Architecture

ViCA2 is a multimodal vision-language model focused on video understanding and visual-spatial cognition tasks.

Indus-Retriever is a dual-encoder sentence transformation model fine-tuned from the nasa-smd-ibm-v0.1 encoder model, specifically designed for natural language processing tasks under NASA's Science Mission Directorate (SMD) to enhance information retrieval and intelligent search capabilities.

ALIGN is a vision-language dual-encoder model that aligns image and text representations through contrastive learning, achieving state-of-the-art cross-modal representation with large-scale noisy data.

DRAGON+ is a dense retrieval model based on the BERT architecture, employing an asymmetric dual-encoder architecture, suitable for text retrieval tasks.

DRAGON+ is a dense retrieval model based on the BERT architecture, with initial weights derived from RetroMAE and trained on enhanced data from the MS MARCO corpus.

An unsupervised sentence encoder based on RoBERTa-large, trained with self-distillation and mutual distillation techniques, suitable for sentence similarity calculation tasks.