Ritchie Zhao

Nvidia (United States) — United States

Computer Science · Physical Sciences

17h-index1.6kcitations36works0.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(14), Parallel Computing and Optimization Techniques(11), Interconnection Networks and Systems(9), Embedded Systems Design Techniques(9), Anomaly Detection Techniques and Applications(6)

Publications36 total

MedPTQ: a practical pipeline for real post-training quantization in 3D medical image segmentation
Journal of Medical Imaging·2026Open Access
Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens
arXiv (Cornell University)·2025Open Access
EMPIRIC: Exploring Missing Pieces in KV Cache Compression for Reducing Computation, Storage, and Latency in Long-Context LLM Inference
ACM SIGOPS Operating Systems Review·2025
Helix Parallelism: Rethinking Sharding Strategies for Interactive Multi-Million-Token LLM Decoding
arXiv (Cornell University)·2025Open Access
Beyond the Buzz: A Pragmatic Take on Inference Disaggregation
arXiv (Cornell University)·2025Open Access
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
2025· 3 citedOpen Access
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
arXiv (Cornell University)·2025Open Access
Post-Training Quantization for 3D Medical Image Segmentation: A Practical Study on Real Inference Engines
arXiv (Cornell University)·2025Open Access
Microscaling Data Formats for Deep Learning
arXiv (Cornell University)·2023· 8 citedOpen Access
With Shared Microexponents, A Little Shifting Goes a Long Way
2023· 33 cited
With Shared Microexponents, A Little Shifting Goes a Long Way
arXiv (Cornell University)·2023Open Access
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point
Neural Information Processing Systems·2020· 54 cited
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations
arXiv (Cornell University)·2020· 2 citedOpen Access
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations
arXiv (Cornell University)·2020· 16 citedOpen Access
Evaluating Celerity: A 16-nm 695 Giga-RISC-V Instructions/s Manycore Processor With Synthesizable PLL
IEEE Solid-State Circuits Letters·2019· 21 cited
OverQ: Opportunistic Outlier Quantization for Neural Network Accelerators
arXiv (Cornell University)·2019· 3 citedOpen Access
Overwrite Quantization: Opportunistic Outlier Handling for Neural Network Accelerators.
arXiv (Cornell University)·2019· 4 citedOpen Access
Building Efficient Deep Neural Networks With Unitary Group Convolutions
2019· 31 cited
A 1.4 GHz 695 Giga Risc-V Inst/s 496-Core Manycore Processor With Mesh On-Chip Network and an All-Digital Synthesized PLL in 16nm CMOS
2019· 18 cited
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
International Conference on Machine Learning·2019· 89 cited
page 1 of 2Next →

Frequent Co-authors

Zhiru Zhang(23), Bita Darvish Rouhani(9), Steve Dai(9), Gai Liu(8), Christopher De(7), Jordan Dotzel(6), Yuwei Hu(5), Christopher Batten(5), Maximilian Golub(5), Rajesh K. Gupta(4), Doug Burger(4), Ankit More(4), Tianwei Xing(3), Jeng-Hau Lin(3), Mani Srivastava(3), Eric S. Chung(3), Scott Davidson(3), Shaolin Xie(3), Christopher Torng(3), Austin Rovinski(3)