Demo model for DREAM Llava-vicuna base.
github links: https://github.com/sai-lab-nyu/dream
@misc{hu2025dreamdraftingrefinedtarget,
title={DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding},
author={Yunhai Hu and Tianhua Xia and Zining Liu and Rahul Raman and Xingyu Liu and Bo Bao and Eric Sather and Vithursan Thangarasa and Sai Qian Zhang},
year={2025},
eprint={2505.19201},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.19201},
}
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support