paper-with-me

Papers

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions

2024-11-12 · Anas Awadalla, Le Xue, Manli Shu, An Yan, Jun Wang, Senthil Purushwalkam, Sheng Shen, Hannah Lee, Oscar Lo, Jae Sung Park, Etash Guha, Silvio Savarese, Ludwig Schmidt, Yejin Choi, Caiming Xiong, ran Xu

We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text. KALE augments synthetic dense image captions with web-scale alt-text to generate factually grounded image captions. Our two-stage approach leverages large vision-language models and language models to create knowledge-augmented captions, which are then used to train a specialized VLM for scaling up the dataset. We train vision-language models on KALE and demonstrate improvements on vision-language tasks. Our experiments show the utility of KALE for training more capable and knowledgeable multimodal models. We release the KALE dataset at https://huggingface.co/datasets/Salesforce/blip3-kale

📄 PDF Abstract BibTeX arXiv:2411.07461

Code (0)

등록된 구현이 없습니다.

Tasks

DescriptiveImage Captioning

Similar Papers 제목 키워드 기반

KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph

2024-09-17 · Yanbei Jiang, Krista A. Ehinger, Jey Han Lau

Exploring the narratives conveyed by fine-art paintings is a challenge in image captioning, where the goal is to generate descriptions that not only precisely represent the visual content but also offer a in-depth interp…

cross-modal alignmentImage CaptioningLanguage ModelingLanguage Modelling

RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training

2024-10-18 · Muhe Ding, Yang Ma, Pengda Qin, Jianlong Wu 외

Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. MLLMs involve significant external k…

DenoisingQuestion AnsweringRetrieval

KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning

2026-01-12 · Qitan Lv, Tianyu Liu, Qiaosheng Zhang, Xingcheng Xu 외 arxiv

Despite the impressive performance of large language models (LLMs) pretrained on vast knowledge corpora, advancing their knowledge manipulation-the ability to effectively recall, reason, and transfer relevant knowledge-r…

Knowledge Graphs

Neural Kaleidoscopic Space Sculpting

2023-01-01 · CVPR 2023 1 · Byeongjoo Ahn, Michael De Zeeuw, Ioannis Gkioulekas, Aswin C. Sankaranarayanan

We introduce a method that recovers full-surround 3D reconstructions from a single kaleidoscopic image using a neural surface representation. Full-surround 3D reconstruction is critical for many applications, such as…

3D Reconstruction

Live Forensics for Distributed Storage Systems

2019-07-24 · Saurabh Jha, Shengkun Cui, Tianyin Xu, Jeremy Enos 외

We present Kaleidoscope an innovative system that supports live forensics for application performance problems caused by either individual component failures or resource contention issues in large-scale distributed stora…

Attribute