Yuhui Xu
9 papers · 2020–2025 · 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 ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(19)
🏆
Keyword Champion
(2)
Top co-authors
Research topics
Machine Learning
(9)
Application Areas
(7)
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(5)
Optimization & Theory · Machine Learning
(4)
Techniques
(4)
Optimization & Theory · Deep Learning
(2)
Natural Language Processing
(1)
Architectures
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Resources & Methods
(1)
Keywords
parameter-efficient fine-tuning
(3)
model compression
(3)
neural architecture search
(2)
model quantization
(2)
large language model
(2)
deployment efficiency
(2)
rank correlation
(1)
inference efficiency
(1)
weight sharing
(1)
memory optimization
(1)
graph convolutional network
(1)
efficient deployment
(1)
parameter efficiency
(1)
speculative decoding
(1)
low-rank adaptation
(1)
key-value cache
(1)
long context
(1)
inference speed
(1)
draft model
(1)
reward model
(1)
Papers
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments
ACL 2025
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
ICML 2025
ThinK: Thinner Key Cache by Query-Driven Pruning
ICLR 2025
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
ACL 2024
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
ICLR 2024
SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
ICML 2024
Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
AAAI 2021
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
ICLR 2020
TRP: Trained Rank Pruning for Efficient Deep Neural Networks
IJCAI 2020