GitHub

Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment

This repository implements the method for training multilingual sentence embeddings in the paper Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment. Abstract: ...
GitHub

VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models

# For LLaVA: bash bash/llava_apgd.sh bash bash/llava_ensemble.sh # For OpenFlamingo: bash bash/of_eval_9B_apgd.sh For captioning and VQA tasks, evaluation can be performed by modifying the -- ...