Zhuohan Li
12 papers · 2018–2024 · 5 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (28)
π§¬
Topic Evolution
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(60)
Venues
Top co-authors
Research topics
Machine Learning
(10)
Deep Learning
(8)
Application Areas
(6)
Optimization & Theory Β· Machine Learning
(6)
Natural Language Processing
(5)
Techniques
(5)
Artificial Intelligence
(3)
Core AI
(3)
Learning Types
(3)
Resources & Methods
(3)
Applications
(2)
Core Methods
(2)
Generation
(2)
Models
(2)
Optimization & Theory Β· Deep Learning
(2)
Keywords
model compression
(3)
large language model
(3)
model parallelism
(3)
machine translation
(2)
distributed training
(2)
neural machine translation
(1)
low-rank approximation
(1)
benchmark evaluation
(1)
deep learning
(1)
instruction following
(1)
knowledge distillation
(1)
network pruning
(1)
dynamic programming
(1)
long short-term memory
(1)
deep learning model
(1)
word alignment
(1)
batch processing
(1)
recurrent neural network
(1)
pipeline parallelism
(1)
knowledge transfer
(1)
Papers
Fairness in Serving Large Language Models
OSDI 2024
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
ICLR 2024
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
OSDI 2023
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
ICML 2023
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
NeurIPS 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
Efficient Training of BERT by Progressively Stacking
ICML 2019
Fast Structured Decoding for Sequence Models
NeurIPS 2019
Hint-Based Training for Non-Autoregressive Machine Translation
EMNLP 2019
Towards Binary-Valued Gates for Robust LSTM Training
ICML 2018