Search Results for author:
Found 3 papers, 0 papers with code
On the Audio Hallucinations in Large Audio-Video Language Models
This paper refers to this as audio hallucinations and analyzes them in large audio-video language models.
Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval
The zero-shot QASIR yields two discoveries: (1) it enables VLMs to generalize to super images and (2) the grid size $N$, image resolution, and VLM size are key trade-off parameters between performance and computation costs.
Leveraging Image-Text Similarity and Caption Modification for the DataComp Challenge: Filtering Track and BYOD Track
Our solution adopts large multimodal models CLIP and BLIP-2 to filter and modify web crawl data, and utilize external datasets along with a bag of tricks to improve the data quality.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
