Scholar
Ritchie Zhao
Google Scholar ID: 8dswaWgAAAAJ
NVIDIA
computer science
computer architecture
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,433
H-index
21
i10-index
26
Publications
20
Co-authors
16
list available
Contact
Email
rz252@cornell.edu
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
11 items
SPIN: Shadow Predictive Indexer for Sparse Attention
2026
Cited
0
Rethinking Heterogeneous System Disaggregation for Subquadratic Attention
2026
Cited
0
Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
2026
Cited
0
Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation
2026
Cited
0
LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts
2026
Cited
1
Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens
2025
Cited
0
Helix Parallelism: Rethinking Sharding Strategies for Interactive Multi-Million-Token LLM Decoding
2025
Cited
0
Beyond the Buzz: A Pragmatic Take on Inference Disaggregation
2025
Cited
0
Load more
Co-authors
13 total
Zhiru Zhang
Cornell University
Eric S Chung
VP of AI Computing, NVIDIA
Bita Darvish Rouhani
Distinguished Engineer, NVIDIA
Steve Dai
NVIDIA Research
Doug Burger
Corporate VP, Managing Director, Microsoft Research Core
Jordan Dotzel
Cornell University
Christopher De Sa
Associate Professor of Computer Science, Cornell University
Christopher Batten
Cornell University
