all AI news
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
May 7, 2024, 4:45 a.m. | Ziqi Pang, Ziyang Xie, Yunze Man, Yu-Xiong Wang
cs.LG updates on arXiv.org arxiv.org
Abstract: This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language. Even more intriguingly, this can be achieved by a simple yet previously overlooked strategy -- employing a frozen transformer block from pre-trained LLMs as a constituent encoder layer to directly process visual tokens. Our work pushes the boundaries of leveraging LLMs for computer vision tasks, significantly departing …
arxiv cs.ai cs.cl cs.cv cs.lg encoder language language models transformers type visual
More from arxiv.org / cs.LG updates on arXiv.org
Efficient Data-Driven MPC for Demand Response of Commercial Buildings
2 days, 15 hours ago |
arxiv.org
Testing the Segment Anything Model on radiology data
2 days, 15 hours ago |
arxiv.org
Calorimeter shower superresolution
2 days, 15 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US