all AI news
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
April 3, 2024, 4:43 a.m. | Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
cs.LG updates on arXiv.org arxiv.org
Abstract: An increasing number of vision-language tasks can be handled with little to no training, i.e., in a zero and few-shot manner, by marrying large language models (LLMs) to vision encoders, resulting in large vision-language models (LVLMs). While this has huge upsides, such as not requiring training data or custom architectures, how an input is presented to an LVLM can have a major impact on zero-shot model performance. In particular, inputs phrased in an underspecified way …
abstract arxiv cs.ai cs.cl cs.cv cs.lg few-shot language language models large language large language models llms questions reason rephrase tasks training type vision vision-language models visual
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US