Search Results for author:
Found 6 papers, 2 papers with code
Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting
Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited.
Enhance the Robustness of Text-Centric Multimodal Alignments
This study assesses the quality and robustness of multimodal representations in the presence of missing entries, noise, or absent modalities, revealing that current text-centric alignment methods compromise downstream robustness.
Text-centric Alignment for Multi-Modality Learning
This research paper addresses the challenge of modality mismatch in multimodal learning, where the modalities available during inference differ from those available at training.
Sampling Neural Radiance Fields for Refractive Objects
To tackle this challenging problem, the refractive index of a scene is reconstructed from silhouettes.
MSD-1030: A Well-built Multi-Sense Evaluation Dataset for Sense Representation Models
However, most of these datasets are not designed for evaluating sense embeddings.
GenSense: A Generalized Sense Retrofitting Model
In the experiment, we show that the generalized model can outperform previous approaches in three types of experiment: semantic relatedness, contextual word similarity and semantic difference.
