Zhihao Jia
21 papers · 2012–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
🏃 Academic Marathon (13) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🐣 Hot Topic Early Bird
🌍
Conference Polyglot
(8)
🏃
Academic Marathon
(13)
🧭
Keyword Pioneer
🧬
Topic Evolution
🗃️
Keyword Collector
(80)
🚀
Conference Pioneer
💎
Century Club
(21)
🔥
Unstoppable
(5)
📈
Trend Setter
⚡
Prolific Year
(7)
Conferences
OSDI (6)
NIPS (4)
ICLR (3)
NSDI (3)
ICML (2)
ACL (1)
EMNLP (1)
IJCAI (1)
Top co-authors
Keywords
distributed training
(6)
neural network optimization
(3)
deep neural network
(2)
preemptible instance
(2)
tensor program optimization
(2)
speculative decoding
(2)
graph neural network
(2)
token generation
(2)
large language model
(2)
model parallelism
(2)
communication complexity
(1)
outlier detection
(1)
parallel computing
(1)
dynamic programming
(1)
model serving
(1)
decision making
(1)
adversarial learning
(1)
kernel optimization
(1)
anomaly detection
(1)
graph optimization
(1)
Papers
DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration
EMNLP 2025
Mirage: A Multi-Level Superoptimizer for Tensor Programs
OSDI 2025
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
ICLR 2025
MagicPIG: LSH Sampling for Efficient LLM Generation
ICLR 2025
Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
ACL 2024
Accelerating Iterative Retrieval-augmented Language Model Serving with Speculation
ICML 2024
SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices
NIPS 2024
Communication Bounds for the Distributed Experts Problem
NIPS 2024
Sequoia: Scalable and Robust Speculative Decoding
NIPS 2024
X-former Elucidator: Reviving Efficient Attention for Long Context Language Modeling
IJCAI 2024
Parcae: Proactive, Liveput-Optimized DNN Training on Preemptible Instances
NSDI 2024
Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs
NSDI 2023
EINNET: Optimizing Tensor Programs with Derivation-Based Transformations
OSDI 2023
TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs
NSDI 2023
BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs
NIPS 2022
GradSign: Model Performance Inference with Theoretical Insights
ICLR 2022
Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization
OSDI 2022
Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads
OSDI 2021
PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections
OSDI 2021
Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks
ICML 2018
Improving Integer Security for Systems with KINT
OSDI 2012