Zhenhua Han

7 papers · 2018–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+1 more ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 👥 Mega-Team · Squad

❓ The Questioner

Venues

OSDI (5) AAAI (1) NeurIPS (1)

Top co-authors

Fan Yang (5) Lidong Zhou (4) Lili Qiu (3) Quanlu Zhang (3) Yuqing Yang (3) Chengruidong Zhang (2) Hanyu Zhao (2) Mao Yang (2) Qianhui Wu (1) Shaokang Dong (1)

Research topics

Machine Learning (6) Application Areas (5) Artificial Intelligence (3) Deep Learning (3) Core AI (3) Techniques (3) Computer Science (2) Systems (2) Natural Language Processing (1) Generation (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1)

Keywords

inference optimization (2) gpu scheduling (2) efficient computing (1) resource allocation (1) neural network model (1) cross-modal alignment (1) sparse attention (1) job migration (1) inference acceleration (1) cluster scheduling (1) request orchestration (1) gpu cluster (1) job scheduling (1) deep learning training (1) deep learning (1) hyperparameter search (1) multi-tenant system (1) buddy allocation (1) multi-tenant cluster (1) neural architecture search (1)

Papers

What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study AAAI 2026 MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention NeurIPS 2024 Parrot: Efficient Serving of LLM-based Applications with Semantic Variable OSDI 2024 Optimizing Dynamic Neural Networks with Brainstorm OSDI 2023 HiveD: Sharing a GPU Cluster for Deep Learning with Guarantees OSDI 2020 Retiarii: A Deep Learning Exploratory-Training Framework OSDI 2020 Gandiva: Introspective Cluster Scheduling for Deep Learning OSDI 2018