Views
No views yet
1@inproceedings{vispec,
2 title={ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding},
3 author={Kang, Jialiang and Shu, Han and Li, Wenshuo and Zhai, Yingjie and Chen, Xinghao},
4 booktitle={Annual Conference on Neural Information Processing Systems},
5 year={2025}
6}1@inproceedings{li2024eagle,
2 author = {Yuhui Li and Fangyun Wei and Chao Zhang and Hongyang Zhang},
3 title = {{EAGLE}: Speculative Sampling Requires Rethinking Feature Uncertainty},
4 booktitle = {International Conference on Machine Learning},
5 year = {2024}
6}
7
8@inproceedings{li2024eagle2,
9 author = {Yuhui Li and Fangyun Wei and Chao Zhang and Hongyang Zhang},
10 title = {{EAGLE-2}: Faster Inference of Language Models with Dynamic Draft Trees},
11 booktitle = {Empirical Methods in Natural Language Processing},
12 year = {2024}
13}
14
15@inproceedings{li2025eagle3,
16 author = {Yuhui Li and Fangyun Wei and Chao Zhang and Hongyang Zhang},
17 title = {{EAGLE-3}: Scaling up Inference Acceleration of Large Language Models via Training-Time Test},
18 booktitle = {Annual Conference on Neural Information Processing Systems},
19 year = {2025}
20}