Zhuohan Li
13 papers · 2018–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🌍 Conference Polyglot (6) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (6)
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(6)
📈
Trend Setter
🔥
Unstoppable
(7)
🗃️
Keyword Collector
(58)
💎
Century Club
(13)
Conferences
ICML (5)
OSDI (3)
NIPS (2)
EMNLP (1)
ICLR (1)
IJCNLP (1)
Top co-authors
Research topics
Keywords
model parallelism
(3)
machine translation
(3)
model compression
(3)
distributed training
(2)
inference latency
(2)
non-autoregressive translation
(2)
large language model
(2)
hint-based training
(2)
word alignment
(2)
neural machine translation
(1)
dynamic programming
(1)
low-rank approximation
(1)
benchmark evaluation
(1)
deep learning model
(1)
deep learning
(1)
knowledge distillation
(1)
recurrent neural network
(1)
batch processing
(1)
pipeline parallelism
(1)
long short-term memory
(1)
Papers
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
ICLR 2024
Fairness in Serving Large Language Models
OSDI 2024
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
ICML 2023
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
OSDI 2023
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
NIPS 2023
Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
OSDI 2022
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
ICML 2021
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
ICML 2020
Fast Structured Decoding for Sequence Models
NIPS 2019
Hint-Based Training for Non-Autoregressive Machine Translation
IJCNLP 2019
Efficient Training of BERT by Progressively Stacking
ICML 2019
Hint-Based Training for Non-Autoregressive Machine Translation
EMNLP 2019
Towards Binary-Valued Gates for Robust LSTM Training
ICML 2018