CogVLM: Visual Expert for Pretrained Language Models
akhaliq
Abstract
We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular shallow alignment method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen pretrained language model and image encoder by a trainable visual expert module in the attention and FFN layers. As a result, CogVLM enables deep fusion of vision language features without sacrificing any performance on NLP tasks. CogVLM-17B achieves state-of-the-art performance on 10 classic cross-modal benchmarks, including NoCaps, Flicker30k captioning, RefCOCO, RefCOCO , RefCOCOg, Visual7W, GQA, ScienceQA, VizWiz VQA and TDIUC, and ranks the 2nd on VQAv2, OKVQA, TextVQA, COCO captioning, etc., surpassing or matching PaLI-X 55B. Codes and checkpoints are available at https://github.com/THUDM/CogVLM.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning (2023)
- Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning (2023)
- From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models (2023)
- SimVLG: Simple and Efficient Pretraining of Visual Language Generative Models (2023)
- Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling (2023)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
Revolutionizing Multimodal Learning: Meet CogVLM!
Links 🔗:
👉 Subscribe: https://www.youtube.com/@Arxflix
👉 Twitter: https://x.com/arxflix
👉 LMNT (Partner): https://lmnt.com/
By Arxflix
