Wayne Xiong
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
arXiv 2024
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
arXiv 2024
Integrative Decoding: Improve Factuality via Implicit Self-consistency
arXiv 2024
Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
arXiv 2022
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers