α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Shivaram Venkataraman
Shivaram Venkataraman
3
papers
26
total citations
papers (3)
CHAI: Clustered Head Attention for Efficient LLM Inference
ICML 2024
arXiv
13
citations
Scaling Inference-Efficient Language Models
ICML 2025
arXiv
12
citations
LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models
ICML 2025
arXiv
1
citations