Hongwu Peng
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Multi-Head Low-Rank Attention
arXiv 2026
Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
two-heads-are-better-than-one-test-time
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
arXiv 2024
AutoReP: Automatic ReLU Replacement for Fast Private Network Inference
ICCV 2023 1
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers